Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-03-14 07:37:25 +08:00
Code Issues Releases Wiki Activity

Merge remote-tracking branch 'upstream/master'

Browse Source
This commit is contained in:
Marco Ferragina 2015-11-08 18:51:04 +01:00
commit ef1498dc3c
77 changed files with 2066 additions and 835 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
CONTRIBUTING.md
View File

@ -1,6 +1,6 @@
**Please include the full output of youtube-dl when run with `-v`**.
The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
The output (including the first lines) contains important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist):
@ -114,12 +114,13 @@ If you want to add support for a new site, you can follow this quick list (assum
webpage = self._download_webpage(url, video_id)
# TODO more code goes here, for example ...
title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
return {
'id': video_id,
'title': title,
'description': self._og_search_description(webpage),
'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False),
# TODO more properties (see youtube_dl/extractor/common.py)
}
```

5
README.md
View File

@ -710,12 +710,13 @@ If you want to add support for a new site, you can follow this quick list (assum
webpage = self._download_webpage(url, video_id)
# TODO more code goes here, for example ...
title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
return {
'id': video_id,
'title': title,
'description': self._og_search_description(webpage),
'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False),
# TODO more properties (see youtube_dl/extractor/common.py)
}
```
@ -794,7 +795,7 @@ Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/i
**Please include the full output of youtube-dl when run with `-v`**.
The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
The output (including the first lines) contains important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist):

9
docs/supportedsites.md
View File

@ -53,6 +53,7 @@
- **Bandcamp:album**
- **bbc**: BBC
- **bbc.co.uk**: BBC iPlayer
- **bbc.co.uk:article**: BBC articles
- **BeatportPro**
- **Beeg**
- **BehindKink**
@ -92,6 +93,7 @@
- **Clipsyndicate**
- **Cloudy**
- **Clubic**
- **Clyp**
- **cmt.com**
- **CNET**
- **CNN**
@ -159,6 +161,7 @@
- **facebook**
- **faz.net**
- **fc2**
- **Fczenit**
- **fernsehkritik.tv**
- **Firstpost**
- **FiveTV**
@ -279,7 +282,7 @@
- **macgamestore**: MacGameStore trailers
- **mailru**: Видео@Mail.Ru
- **Malemotion**
- **MDR**
- **MDR**: MDR.DE and KiKA
- **media.ccc.de**
- **metacafe**
- **Metacritic**
@ -514,6 +517,7 @@
- **SSA**
- **stanfordoc**: Stanford Open ClassRoom
- **Steam**
- **Stitcher**
- **streamcloud.eu**
- **StreamCZ**
- **StreetVoice**
@ -587,7 +591,8 @@
- **twitch:stream**
- **twitch:video**
- **twitch:vod**
- **TwitterCard**
- **twitter**
- **twitter:card**
- **Ubu**
- **udemy**
- **udemy:course**

2
setup.py
View File

@ -28,7 +28,7 @@ py2exe_options = {
"compressed": 1,
"optimize": 2,
"dist_dir": '.',
"dll_excludes": ['w9xpopen.exe'],
"dll_excludes": ['w9xpopen.exe', 'crypt32.dll'],
}
py2exe_console = [{

4
test/test_InfoExtractor.py
View File

@ -37,12 +37,16 @@ class TestInfoExtractor(unittest.TestCase):
<meta property='og:image' content='http://domain.com/pic.jpg?key1=val1&amp;key2=val2'/>
<meta content='application/x-shockwave-flash' property='og:video:type'>
<meta content='Foo' property=og:foobar>
<meta name="og:test1" content='foo > < bar'/>
<meta name="og:test2" content="foo >//< bar"/>
'''
self.assertEqual(ie._og_search_title(html), 'Foo')
self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2')
self.assertEqual(ie._og_search_video_url(html, default=None), None)
self.assertEqual(ie._og_search_property('foobar', html), 'Foo')
self.assertEqual(ie._og_search_property('test1', html), 'foo > < bar')
self.assertEqual(ie._og_search_property('test2', html), 'foo >//< bar')
def test_html_search_meta(self):
ie = self.ie

17
test/test_compat.py
View File

@ -13,8 +13,10 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.utils import get_filesystem_encoding
from youtube_dl.compat import (
compat_getenv,
compat_etree_fromstring,
compat_expanduser,
compat_shlex_split,
compat_str,
compat_urllib_parse_unquote,
compat_urllib_parse_unquote_plus,
)
@ -71,5 +73,20 @@ class TestCompat(unittest.TestCase):
def test_compat_shlex_split(self):
self.assertEqual(compat_shlex_split('-option "one two"'), ['-option', 'one two'])
def test_compat_etree_fromstring(self):
xml = '''
<root foo="bar" spam="中文">
<normal>foo</normal>
<chinese>中文</chinese>
<foo><bar>spam</bar></foo>
</root>
'''
doc = compat_etree_fromstring(xml.encode('utf-8'))
self.assertTrue(isinstance(doc.attrib['foo'], compat_str))
self.assertTrue(isinstance(doc.attrib['spam'], compat_str))
self.assertTrue(isinstance(doc.find('normal').text, compat_str))
self.assertTrue(isinstance(doc.find('chinese').text, compat_str))
self.assertTrue(isinstance(doc.find('foo/bar').text, compat_str))
if __name__ == '__main__':
unittest.main()

2
test/test_download.py
View File

@ -102,7 +102,7 @@ def generator(test_case):
params = get_params(test_case.get('params', {}))
if is_playlist and 'playlist' not in test_case:
params.setdefault('extract_flat', True)
params.setdefault('extract_flat', 'in_playlist')
params.setdefault('skip_download', True)
ydl = YoutubeDL(params, auto_init=False)

21
test/test_subtitles.py
View File

@ -28,6 +28,7 @@ from youtube_dl.extractor import (
ThePlatformFeedIE,
RTVEALaCartaIE,
FunnyOrDieIE,
DemocracynowIE,
)
@ -346,5 +347,25 @@ class TestFunnyOrDieSubtitles(BaseTestSubtitles):
self.assertEqual(md5(subtitles['en']), 'c5593c193eacd353596c11c2d4f9ecc4')
class TestDemocracynowSubtitles(BaseTestSubtitles):
url = 'http://www.democracynow.org/shows/2015/7/3'
IE = DemocracynowIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), 'acaca989e24a9e45a6719c9b3d60815c')
def test_subtitles_in_page(self):
self.url = 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree'
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), 'acaca989e24a9e45a6719c9b3d60815c')
if __name__ == '__main__':
unittest.main()

24
test/test_utils.py
View File

@ -68,6 +68,9 @@ from youtube_dl.utils import (
cli_valueless_option,
cli_bool_option,
)
from youtube_dl.compat import (
compat_etree_fromstring,
)
class TestUtil(unittest.TestCase):
@ -233,6 +236,7 @@ class TestUtil(unittest.TestCase):
unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
'20150202')
self.assertEqual(unified_strdate('25-09-2014'), '20140925')
self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
def test_find_xpath_attr(self):
testxml = '''<root>
@ -242,7 +246,7 @@ class TestUtil(unittest.TestCase):
<node x="b" y="d" />
<node x="" />
</root>'''
doc = xml.etree.ElementTree.fromstring(testxml)
doc = compat_etree_fromstring(testxml)
self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n'), None)
self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
@ -263,7 +267,7 @@ class TestUtil(unittest.TestCase):
<url>http://server.com/download.mp3</url>
</media:song>
</root>'''
doc = xml.etree.ElementTree.fromstring(testxml)
doc = compat_etree_fromstring(testxml)
find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
self.assertTrue(find('media:song') is not None)
self.assertEqual(find('media:song/media:author').text, 'The Author')
@ -275,9 +279,16 @@ class TestUtil(unittest.TestCase):
p = xml.etree.ElementTree.SubElement(div, 'p')
p.text = 'Foo'
self.assertEqual(xpath_element(doc, 'div/p'), p)
self.assertEqual(xpath_element(doc, ['div/p']), p)
self.assertEqual(xpath_element(doc, ['div/bar', 'div/p']), p)
self.assertEqual(xpath_element(doc, 'div/bar', default='default'), 'default')
self.assertEqual(xpath_element(doc, ['div/bar'], default='default'), 'default')
self.assertTrue(xpath_element(doc, 'div/bar') is None)
self.assertTrue(xpath_element(doc, ['div/bar']) is None)
self.assertTrue(xpath_element(doc, ['div/bar'], 'div/baz') is None)
self.assertRaises(ExtractorError, xpath_element, doc, 'div/bar', fatal=True)
self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar'], fatal=True)
self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar', 'div/baz'], fatal=True)
def test_xpath_text(self):
testxml = '''<root>
@ -285,7 +296,7 @@ class TestUtil(unittest.TestCase):
<p>Foo</p>
</div>
</root>'''
doc = xml.etree.ElementTree.fromstring(testxml)
doc = compat_etree_fromstring(testxml)
self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
self.assertEqual(xpath_text(doc, 'div/bar', default='default'), 'default')
self.assertTrue(xpath_text(doc, 'div/bar') is None)
@ -297,7 +308,7 @@ class TestUtil(unittest.TestCase):
<p x="a">Foo</p>
</div>
</root>'''
doc = xml.etree.ElementTree.fromstring(testxml)
doc = compat_etree_fromstring(testxml)
self.assertEqual(xpath_attr(doc, 'div/p', 'x'), 'a')
self.assertEqual(xpath_attr(doc, 'div/bar', 'x'), None)
self.assertEqual(xpath_attr(doc, 'div/p', 'y'), None)
@ -425,6 +436,8 @@ class TestUtil(unittest.TestCase):
self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
self.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251)
self.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None)
def test_strip_jsonp(self):
stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
@ -495,6 +508,9 @@ class TestUtil(unittest.TestCase):
"playlist":[{"controls":{"all":null}}]
}''')
inp = '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"'''
self.assertEqual(js_to_json(inp), '''"The CW's 'Crazy Ex-Girlfriend'"''')
inp = '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
json_code = js_to_json(inp)
self.assertEqual(json.loads(json_code), json.loads(inp))

9
test/test_youtube_lists.py
View File

@ -57,5 +57,14 @@ class TestYoutubeLists(unittest.TestCase):
entries = result['entries']
self.assertEqual(len(entries), 100)
def test_youtube_flat_playlist_titles(self):
dl = FakeYDL()
dl.params['extract_flat'] = True
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
self.assertIsPlaylist(result)
for entry in result['entries']:
self.assertTrue(entry.get('title'))
if __name__ == '__main__':
unittest.main()

8
youtube_dl/YoutubeDL.py
View File

@ -37,6 +37,7 @@ from .compat import (
compat_tokenize_tokenize,
compat_urllib_error,
compat_urllib_request,
compat_urllib_request_DataHandler,
)
from .utils import (
ContentTooShortError,
@ -571,7 +572,7 @@ class YoutubeDL(object):
if v is not None)
template_dict = collections.defaultdict(lambda: 'NA', template_dict)
outtmpl = sanitize_path(self.params.get('outtmpl', DEFAULT_OUTTMPL))
outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
tmpl = compat_expanduser(outtmpl)
filename = tmpl % template_dict
# Temporary fix for #4787
@ -579,7 +580,7 @@ class YoutubeDL(object):
# to workaround encoding issues with subprocess on python2 @ Windows
if sys.version_info < (3, 0) and sys.platform == 'win32':
filename = encodeFilename(filename, True).decode(preferredencoding())
return filename
return sanitize_path(filename)
except ValueError as err:
self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
return None
@ -1967,8 +1968,9 @@ class YoutubeDL(object):
debuglevel = 1 if self.params.get('debug_printtraffic') else 0
https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel)
ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel)
data_handler = compat_urllib_request_DataHandler()
opener = compat_urllib_request.build_opener(
proxy_handler, https_handler, cookie_processor, ydlh)
proxy_handler, https_handler, cookie_processor, ydlh, data_handler)
# Delete the default user-agent header, which would otherwise apply in
# cases where our custom HTTP handler doesn't come into play

83
youtube_dl/compat.py
View File

@ -1,7 +1,10 @@
from __future__ import unicode_literals
import binascii
import collections
import email
import getpass
import io
import optparse
import os
import re
@ -11,6 +14,7 @@ import socket
import subprocess
import sys
import itertools
import xml.etree.ElementTree
try:
@ -38,6 +42,11 @@ try:
except ImportError: # Python 2
import urlparse as compat_urlparse
try:
import urllib.response as compat_urllib_response
except ImportError: # Python 2
import urllib as compat_urllib_response
try:
import http.cookiejar as compat_cookiejar
except ImportError: # Python 2
@ -155,6 +164,40 @@ except ImportError: # Python 2
string = string.replace('+', ' ')
return compat_urllib_parse_unquote(string, encoding, errors)
try:
from urllib.request import DataHandler as compat_urllib_request_DataHandler
except ImportError: # Python < 3.4
# Ported from CPython 98774:1733b3bd46db, Lib/urllib/request.py
class compat_urllib_request_DataHandler(compat_urllib_request.BaseHandler):
def data_open(self, req):
# data URLs as specified in RFC 2397.
#
# ignores POSTed data
#
# syntax:
# dataurl := "data:" [ mediatype ] [ ";base64" ] "," data
# mediatype := [ type "/" subtype ] *( ";" parameter )
# data := *urlchar
# parameter := attribute "=" value
url = req.get_full_url()
scheme, data = url.split(":", 1)
mediatype, data = data.split(",", 1)
# even base64 encoded data URLs might be quoted so unquote in any case:
data = compat_urllib_parse_unquote_to_bytes(data)
if mediatype.endswith(";base64"):
data = binascii.a2b_base64(data)
mediatype = mediatype[:-7]
if not mediatype:
mediatype = "text/plain;charset=US-ASCII"
headers = email.message_from_string(
"Content-type: %s\nContent-length: %d\n" % (mediatype, len(data)))
return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url)
try:
compat_basestring = basestring # Python 2
except NameError:
@ -170,6 +213,43 @@ try:
except ImportError: # Python 2.6
from xml.parsers.expat import ExpatError as compat_xml_parse_error
if sys.version_info[0] >= 3:
compat_etree_fromstring = xml.etree.ElementTree.fromstring
else:
# python 2.x tries to encode unicode strings with ascii (see the
# XMLParser._fixtext method)
etree = xml.etree.ElementTree
try:
_etree_iter = etree.Element.iter
except AttributeError: # Python <=2.6
def _etree_iter(root):
for el in root.findall('*'):
yield el
for sub in _etree_iter(el):
yield sub
# on 2.6 XML doesn't have a parser argument, function copied from CPython
# 2.7 source
def _XML(text, parser=None):
if not parser:
parser = etree.XMLParser(target=etree.TreeBuilder())
parser.feed(text)
return parser.close()
def _element_factory(*args, **kwargs):
el = etree.Element(*args, **kwargs)
for k, v in el.items():
if isinstance(v, bytes):
el.set(k, v.decode('utf-8'))
return el
def compat_etree_fromstring(text):
doc = _XML(text, parser=etree.XMLParser(target=etree.TreeBuilder(element_factory=_element_factory)))
for el in _etree_iter(doc):
if el.text is not None and isinstance(el.text, bytes):
el.text = el.text.decode('utf-8')
return doc
try:
from urllib.parse import parse_qs as compat_parse_qs
@ -465,6 +545,7 @@ __all__ = [
'compat_chr',
'compat_cookiejar',
'compat_cookies',
'compat_etree_fromstring',
'compat_expanduser',
'compat_get_terminal_size',
'compat_getenv',
@ -489,6 +570,8 @@ __all__ = [
'compat_urllib_parse_unquote_to_bytes',
'compat_urllib_parse_urlparse',
'compat_urllib_request',
'compat_urllib_request_DataHandler',
'compat_urllib_response',
'compat_urlparse',
'compat_urlretrieve',
'compat_xml_parse_error',

22
youtube_dl/downloader/f4m.py
View File

@ -5,12 +5,13 @@ import io
import itertools
import os
import time
import xml.etree.ElementTree as etree
from .fragment import FragmentFD
from ..compat import (
compat_etree_fromstring,
compat_urlparse,
compat_urllib_error,
compat_urllib_parse_urlparse,
)
from ..utils import (
encodeFilename,
@ -285,9 +286,11 @@ class F4mFD(FragmentFD):
man_url = info_dict['url']
requested_bitrate = info_dict.get('tbr')
self.to_screen('[%s] Downloading f4m manifest' % self.FD_NAME)
manifest = self.ydl.urlopen(man_url).read()
urlh = self.ydl.urlopen(man_url)
man_url = urlh.geturl()
manifest = urlh.read()
doc = etree.fromstring(manifest)
doc = compat_etree_fromstring(manifest)
formats = [(int(f.attrib.get('bitrate', -1)), f)
for f in self._get_unencrypted_media(doc)]
if requested_bitrate is None:
@ -329,20 +332,25 @@ class F4mFD(FragmentFD):
if not live:
write_metadata_tag(dest_stream, metadata)
base_url_parsed = compat_urllib_parse_urlparse(base_url)
self._start_frag_download(ctx)
frags_filenames = []
while fragments_list:
seg_i, frag_i = fragments_list.pop(0)
name = 'Seg%d-Frag%d' % (seg_i, frag_i)
url = base_url + name
query = []
if base_url_parsed.query:
query.append(base_url_parsed.query)
if akamai_pv:
url += '?' + akamai_pv.strip(';')
query.append(akamai_pv.strip(';'))
if info_dict.get('extra_param_to_segment_url'):
url += info_dict.get('extra_param_to_segment_url')
query.append(info_dict['extra_param_to_segment_url'])
url_parsed = base_url_parsed._replace(path=base_url_parsed.path + name, query='&'.join(query))
frag_filename = '%s-%s' % (ctx['tmpfilename'], name)
try:
success = ctx['dl'].download(frag_filename, {'url': url})
success = ctx['dl'].download(frag_filename, {'url': url_parsed.geturl()})
if not success:
return False
(down, frag_sanitized) = sanitize_open(frag_filename, 'rb')

2
youtube_dl/downloader/hls.py
View File

@ -30,7 +30,7 @@ class HlsFD(FileDownloader):
args = [ffpp.executable, '-y']
if info_dict['http_headers']:
if info_dict['http_headers'] and re.match(r'^https?://', url):
# Trailing \r\n after each HTTP header is important to prevent warning from ffmpeg/avconv:
# [http @ 00000000003d2fa0] No trailing CRLF found in HTTP header.
args += [

13
youtube_dl/extractor/__init__.py
View File

@ -45,6 +45,7 @@ from .bambuser import BambuserIE, BambuserChannelIE
from .bandcamp import BandcampIE, BandcampAlbumIE
from .bbc import (
BBCCoUkIE,
BBCCoUkArticleIE,
BBCIE,
)
from .beeg import BeegIE
@ -89,6 +90,7 @@ from .cliphunter import CliphunterIE
from .clipsyndicate import ClipsyndicateIE
from .cloudy import CloudyIE
from .clubic import ClubicIE
from .clyp import ClypIE
from .cmt import CMTIE
from .cnet import CNETIE
from .cnn import (
@ -122,6 +124,7 @@ from .dbtv import DBTVIE
from .dcn import DCNIE
from .dctp import DctpTvIE
from .deezer import DeezerPlaylistIE
from .democracynow import DemocracynowIE
from .dfb import DFBIE
from .dhm import DHMIE
from .dotsub import DotsubIE
@ -209,7 +212,10 @@ from .gfycat import GfycatIE
from .giantbomb import GiantBombIE
from .giga import GigaIE
from .glide import GlideIE
from .globo import GloboIE
from .globo import (
GloboIE,
GloboArticleIE,
)
from .godtube import GodTubeIE
from .goldenmoustache import GoldenMoustacheIE
from .golem import GolemIE
@ -586,6 +592,7 @@ from .spankwire import SpankwireIE
from .spiegel import SpiegelIE, SpiegelArticleIE
from .spiegeltv import SpiegeltvIE
from .spike import SpikeIE
from .stitcher import StitcherIE
from .sport5 import Sport5IE
from .sportbox import (
SportBoxIE,
@ -690,7 +697,7 @@ from .twitch import (
TwitchBookmarksIE,
TwitchStreamIE,
)
from .twitter import TwitterCardIE
from .twitter import TwitterCardIE, TwitterIE
from .ubu import UbuIE
from .udemy import (
UdemyIE,
@ -717,7 +724,6 @@ from .vh1 import VH1IE
from .vice import ViceIE
from .viddler import ViddlerIE
from .videodetective import VideoDetectiveIE
from .videolecturesnet import VideoLecturesNetIE
from .videofyme import VideofyMeIE
from .videomega import VideoMegaIE
from .videopremium import VideoPremiumIE
@ -728,6 +734,7 @@ from .vidto import VidtoIE
from .vidzi import VidziIE
from .vier import VierIE, VierVideosIE
from .viewster import ViewsterIE
from .viidea import ViideaIE
from .vimeo import (
VimeoIE,
VimeoAlbumIE,

18
youtube_dl/extractor/abc.py
View File

@ -12,7 +12,7 @@ from ..utils import (
class ABCIE(InfoExtractor):
IE_NAME = 'abc.net.au'
_VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P<id>\d+)'
_VALID_URL = r'http://www\.abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
@ -36,6 +36,18 @@ class ABCIE(InfoExtractor):
'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill',
},
'add_ie': ['Youtube'],
}, {
'url': 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080',
'md5': 'b96eee7c9edf4fc5a358a0252881cc1f',
'info_dict': {
'id': '6880080',
'ext': 'mp3',
'title': 'NAB lifts interest rates, following Westpac and CBA',
'description': 'md5:f13d8edc81e462fce4a0437c7dc04728',
},
}, {
'url': 'http://www.abc.net.au/news/2015-10-19/6866214',
'only_matching': True,
}]
def _real_extract(self, url):
@ -43,7 +55,7 @@ class ABCIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
mobj = re.search(
r'inline(?P<type>Video|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
r'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
webpage)
if mobj is None:
raise ExtractorError('Unable to extract video urls')
@ -60,11 +72,13 @@ class ABCIE(InfoExtractor):
formats = [{
'url': url_info['url'],
'vcodec': url_info.get('codec') if mobj.group('type') == 'Video' else 'none',
'width': int_or_none(url_info.get('width')),
'height': int_or_none(url_info.get('height')),
'tbr': int_or_none(url_info.get('bitrate')),
'filesize': int_or_none(url_info.get('filesize')),
} for url_info in urls_info]
self._sort_formats(formats)
return {

2
youtube_dl/extractor/adultswim.py
View File

@ -183,7 +183,7 @@ class AdultSwimIE(InfoExtractor):
media_url = file_el.text
if determine_ext(media_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
media_url, segment_title, 'mp4', 'm3u8_native', preference=0, m3u8_id='hls'))
media_url, segment_title, 'mp4', preference=0, m3u8_id='hls'))
else:
formats.append({
'format_id': '%s_%s' % (bitrate, ftype),

4
youtube_dl/extractor/anitube.py
View File

@ -26,8 +26,8 @@ class AnitubeIE(InfoExtractor):
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
key = self._html_search_regex(
r'http://www\.anitube\.se/embed/([A-Za-z0-9_-]*)', webpage, 'key')
key = self._search_regex(
r'src=["\']https?://[^/]+/embed/([A-Za-z0-9_-]+)', webpage, 'key')
config_xml = self._download_xml(
'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, key)

4
youtube_dl/extractor/ard.py
View File

@ -14,8 +14,8 @@ from ..utils import (
parse_duration,
unified_strdate,
xpath_text,
parse_xml,
)
from ..compat import compat_etree_fromstring
class ARDMediathekIE(InfoExtractor):
@ -161,7 +161,7 @@ class ARDMediathekIE(InfoExtractor):
raise ExtractorError('This program is only suitable for those aged 12 and older. Video %s is therefore only available between 20 pm and 6 am.' % video_id, expected=True)
if re.search(r'[\?&]rss($|[=&])', url):
doc = parse_xml(webpage)
doc = compat_etree_fromstring(webpage.encode('utf-8'))
if doc.tag == 'rss':
return GenericIE()._extract_rss(url, video_id, doc)

8
youtube_dl/extractor/bandcamp.py
View File

@ -10,6 +10,8 @@ from ..compat import (
)
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
)
@ -52,11 +54,11 @@ class BandcampIE(InfoExtractor):
ext, abr_str = format_id.split('-', 1)
formats.append({
'format_id': format_id,
'url': format_url,
'url': self._proto_relative_url(format_url, 'http:'),
'ext': ext,
'vcodec': 'none',
'acodec': ext,
'abr': int(abr_str),
'abr': int_or_none(abr_str),
})
self._sort_formats(formats)
@ -65,7 +67,7 @@ class BandcampIE(InfoExtractor):
'id': compat_str(data['id']),
'title': data['title'],
'formats': formats,
'duration': float(data['duration']),
'duration': float_or_none(data.get('duration')),
}
else:
raise ExtractorError('No free songs found')

45
youtube_dl/extractor/bbc.py
View File

@ -2,7 +2,6 @@
from __future__ import unicode_literals
import re
import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
@ -14,13 +13,16 @@ from ..utils import (
remove_end,
unescapeHTML,
)
from ..compat import compat_HTTPError
from ..compat import (
compat_etree_fromstring,
compat_HTTPError,
)
class BBCCoUkIE(InfoExtractor):
IE_NAME = 'bbc.co.uk'
IE_DESC = 'BBC iPlayer'
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|iplayer(?:/[^/]+)?/(?:episode/|playlist/))|music/clips[/#])(?P<id>[\da-z]{8})'
_MEDIASELECTOR_URLS = [
# Provides HQ HLS streams with even better quality that pc mediaset but fails
@ -344,7 +346,7 @@ class BBCCoUkIE(InfoExtractor):
url, programme_id, 'Downloading media selection XML')
except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8'))
media_selection = compat_etree_fromstring(ee.cause.read().decode('utf-8'))
else:
raise
return self._process_media_selector(media_selection, programme_id)
@ -421,7 +423,7 @@ class BBCCoUkIE(InfoExtractor):
continue
title = playlist.find('./{%s}title' % self._EMP_PLAYLIST_NS).text
description_el = playlist.find('./{%s}summary' % self._EMP_PLAYLIST_NS)
description = description_el.text if description_el else None
description = description_el.text if description_el is not None else None
def get_programme_id(item):
def get_from_attributes(item):
@ -625,6 +627,7 @@ class BBCIE(BBCCoUkIE):
'id': 'p02xycnp',
'ext': 'mp4',
'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
'description': 'BBC Sport\'s David Ornstein has the latest transfer gossip, including rumours of a Manchester United return for Cristiano Ronaldo.',
'duration': 140,
},
'params': {
@ -651,7 +654,7 @@ class BBCIE(BBCCoUkIE):
@classmethod
def suitable(cls, url):
return False if BBCCoUkIE.suitable(url) else super(BBCIE, cls).suitable(url)
return False if BBCCoUkIE.suitable(url) or BBCCoUkArticleIE.suitable(url) else super(BBCIE, cls).suitable(url)
def _extract_from_media_meta(self, media_meta, video_id):
# Direct links to media in media metadata (e.g.
@ -902,3 +905,33 @@ class BBCIE(BBCCoUkIE):
})
return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
class BBCCoUkArticleIE(InfoExtractor):
_VALID_URL = 'http://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
IE_NAME = 'bbc.co.uk:article'
IE_DESC = 'BBC articles'
_TEST = {
'url': 'http://www.bbc.co.uk/programmes/articles/3jNQLTMrPlYGTBn0WV6M2MS/not-your-typical-role-model-ada-lovelace-the-19th-century-programmer',
'info_dict': {
'id': '3jNQLTMrPlYGTBn0WV6M2MS',
'title': 'Calculating Ada: The Countess of Computing - Not your typical role model: Ada Lovelace the 19th century programmer - BBC Four',
'description': 'Hannah Fry reveals some of her surprising discoveries about Ada Lovelace during filming.',
},
'playlist_count': 4,
'add_ie': ['BBCCoUk'],
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
title = self._og_search_title(webpage)
description = self._og_search_description(webpage).strip()
entries = [self.url_result(programme_url) for programme_url in re.findall(
r'<div[^>]+typeof="Clip"[^>]+resource="([^"]+)"', webpage)]
return self.playlist_result(entries, playlist_id, title, description)

2
youtube_dl/extractor/beeg.py
View File

@ -33,6 +33,8 @@ class BeegIE(InfoExtractor):
formats = []
for format_id, video_url in video.items():
if not video_url:
continue
height = self._search_regex(
r'^(\d+)[pP]$', format_id, 'height', default=None)
if not height:

6
youtube_dl/extractor/bilibili.py
View File

@ -4,9 +4,11 @@ from __future__ import unicode_literals
import re
import itertools
import json
import xml.etree.ElementTree as ET
from .common import InfoExtractor
from ..compat import (
compat_etree_fromstring,
)
from ..utils import (
int_or_none,
unified_strdate,
@ -88,7 +90,7 @@ class BiliBiliIE(InfoExtractor):
except ValueError:
pass
lq_doc = ET.fromstring(lq_page)
lq_doc = compat_etree_fromstring(lq_page)
lq_durls = lq_doc.findall('./durl')
hq_doc = self._download_xml(

4
youtube_dl/extractor/brightcove.py
View File

@ -3,10 +3,10 @@ from __future__ import unicode_literals
import re
import json
import xml.etree.ElementTree
from .common import InfoExtractor
from ..compat import (
compat_etree_fromstring,
compat_parse_qs,
compat_str,
compat_urllib_parse,
@ -119,7 +119,7 @@ class BrightcoveIE(InfoExtractor):
object_str = fix_xml_ampersands(object_str)
try:
object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
object_doc = compat_etree_fromstring(object_str.encode('utf-8'))
except compat_xml_parse_error:
return

43
youtube_dl/extractor/canalc2.py
View File

@ -4,38 +4,53 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import parse_duration
class Canalc2IE(InfoExtractor):
IE_NAME = 'canalc2.tv'
_VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?.*?idVideo=(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?canalc2\.tv/video/(?P<id>\d+)'
_TEST = {
'url': 'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
'url': 'http://www.canalc2.tv/video/12163',
'md5': '060158428b650f896c542dfbb3d6487f',
'info_dict': {
'id': '12163',
'ext': 'mp4',
'title': 'Terrasses du Numérique'
'ext': 'flv',
'title': 'Terrasses du Numérique',
'duration': 122,
},
'params': {
'skip_download': True, # Requires rtmpdump
}
}
def _real_extract(self, url):
video_id = re.match(self._VALID_URL, url).group('id')
# We need to set the voir field for getting the file name
url = 'http://www.canalc2.tv/video.asp?idVideo=%s&voir=oui' % video_id
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
file_name = self._search_regex(
r"so\.addVariable\('file','(.*?)'\);",
webpage, 'file name')
video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name
video_url = self._search_regex(
r'jwplayer\((["\'])Player\1\)\.setup\({[^}]*file\s*:\s*(["\'])(?P<file>.+?)\2',
webpage, 'video_url', group='file')
formats = [{'url': video_url}]
if video_url.startswith('rtmp://'):
rtmp = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+/))(?P<play_path>mp4:.+)$', video_url)
formats[0].update({
'url': rtmp.group('url'),
'ext': 'flv',
'app': rtmp.group('app'),
'play_path': rtmp.group('play_path'),
'page_url': url,
})
title = self._html_search_regex(
r'class="evenement8">(.*?)</a>', webpage, 'title')
r'(?s)class="[^"]*col_description[^"]*">.*?<h3>(.*?)</h3>', webpage, 'title')
duration = parse_duration(self._search_regex(
r'id=["\']video_duree["\'][^>]*>([^<]+)',
webpage, 'duration', fatal=False))
return {
'id': video_id,
'ext': 'mp4',
'url': video_url,
'title': title,
'duration': duration,
'formats': formats,
}

57
youtube_dl/extractor/clyp.py Normal file
View File

@ -0,0 +1,57 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
float_or_none,
parse_iso8601,
)
class ClypIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?clyp\.it/(?P<id>[a-z0-9]+)'
_TEST = {
'url': 'https://clyp.it/ojz2wfah',
'md5': '1d4961036c41247ecfdcc439c0cddcbb',
'info_dict': {
'id': 'ojz2wfah',
'ext': 'mp3',
'title': 'Krisson80 - bits wip wip',
'description': '#Krisson80BitsWipWip #chiptune\n#wip',
'duration': 263.21,
'timestamp': 1443515251,
'upload_date': '20150929',
},
}
def _real_extract(self, url):
audio_id = self._match_id(url)
metadata = self._download_json(
'https://api.clyp.it/%s' % audio_id, audio_id)
formats = []
for secure in ('', 'Secure'):
for ext in ('Ogg', 'Mp3'):
format_id = '%s%s' % (secure, ext)
format_url = metadata.get('%sUrl' % format_id)
if format_url:
formats.append({
'url': format_url,
'format_id': format_id,
'vcodec': 'none',
})
self._sort_formats(formats)
title = metadata['Title']
description = metadata.get('Description')
duration = float_or_none(metadata.get('Duration'))
timestamp = parse_iso8601(metadata.get('DateCreated'))
return {
'id': audio_id,
'title': title,
'description': description,
'duration': duration,
'timestamp': timestamp,
'formats': formats,
}

22
youtube_dl/extractor/common.py
View File

@ -10,13 +10,11 @@ import re
import socket
import sys
import time
import xml.etree.ElementTree
from ..compat import (
compat_cookiejar,
compat_cookies,
compat_getpass,
compat_HTTPError,
compat_http_client,
compat_urllib_error,
compat_urllib_parse,
@ -24,6 +22,7 @@ from ..compat import (
compat_urllib_request,
compat_urlparse,
compat_str,
compat_etree_fromstring,
)
from ..utils import (
NO_DEFAULT,
@ -172,6 +171,7 @@ class InfoExtractor(object):
view_count: How many users have watched the video on the platform.
like_count: Number of positive ratings of the video
dislike_count: Number of negative ratings of the video
repost_count: Number of reposts of the video
average_rating: Average rating give by users, the scale used depends on the webpage
comment_count: Number of comments on the video
comments: A list of comments, each with one or more of the following
@ -310,11 +310,11 @@ class InfoExtractor(object):
@classmethod
def ie_key(cls):
"""A string for getting the InfoExtractor with get_info_extractor"""
return cls.__name__[:-2]
return compat_str(cls.__name__[:-2])
@property
def IE_NAME(self):
return type(self).__name__[:-2]
return compat_str(type(self).__name__[:-2])
def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
""" Returns the response handle """
@ -461,7 +461,7 @@ class InfoExtractor(object):
return xml_string
if transform_source:
xml_string = transform_source(xml_string)
return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8'))
return compat_etree_fromstring(xml_string.encode('utf-8'))
def _download_json(self, url_or_request, video_id,
note='Downloading JSON metadata',
@ -645,7 +645,7 @@ class InfoExtractor(object):
# Helper functions for extracting OpenGraph info
@staticmethod
def _og_regexes(prop):
content_re = r'content=(?:"([^>]+?)"|\'([^>]+?)\'|\s*([^\s"\'=<>`]+?))'
content_re = r'content=(?:"([^"]+?)"|\'([^\']+?)\'|\s*([^\s"\'=<>`]+?))'
property_re = (r'(?:name|property)=(?:\'og:%(prop)s\'|"og:%(prop)s"|\s*og:%(prop)s\b)'
% {'prop': re.escape(prop)})
template = r'<meta[^>]+?%s[^>]+?%s'
@ -841,7 +841,7 @@ class InfoExtractor(object):
self._request_webpage(url, video_id, 'Checking %s URL' % item)
return True
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError):
if isinstance(e.cause, compat_urllib_error.URLError):
self.to_screen(
'%s: %s URL is invalid, skipping' % (video_id, item))
return False
@ -943,13 +943,15 @@ class InfoExtractor(object):
if re.match(r'^https?://', u)
else compat_urlparse.urljoin(m3u8_url, u))
m3u8_doc = self._download_webpage(
res = self._download_webpage_handle(
m3u8_url, video_id,
note=note or 'Downloading m3u8 information',
errnote=errnote or 'Failed to download m3u8 information',
fatal=fatal)
if m3u8_doc is False:
return m3u8_doc
if res is False:
return res
m3u8_doc, urlh = res
m3u8_url = urlh.geturl()
last_info = None
last_media = None
kv_rex = re.compile(

97
youtube_dl/extractor/crunchyroll.py
View File

@ -5,12 +5,12 @@ import re
import json
import base64
import zlib
import xml.etree.ElementTree
from hashlib import sha1
from math import pow, sqrt, floor
from .common import InfoExtractor
from ..compat import (
compat_etree_fromstring,
compat_urllib_parse,
compat_urllib_parse_unquote,
compat_urllib_request,
@ -21,6 +21,7 @@ from ..utils import (
bytes_to_intlist,
intlist_to_bytes,
int_or_none,
lowercase_escape,
remove_end,
unified_strdate,
urlencode_postdata,
@ -32,6 +33,26 @@ from ..aes import (
class CrunchyrollBaseIE(InfoExtractor):
_NETRC_MACHINE = 'crunchyroll'
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
self.report_login()
login_url = 'https://www.crunchyroll.com/?a=formhandler'
data = urlencode_postdata({
'formname': 'RpcApiUser_Login',
'name': username,
'password': password,
})
login_request = compat_urllib_request.Request(login_url, data)
login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
self._download_webpage(login_request, None, False, 'Wrong login info')
def _real_initialize(self):
self._login()
def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None):
request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request)
else compat_urllib_request.Request(url_or_request))
@ -46,10 +67,22 @@ class CrunchyrollBaseIE(InfoExtractor):
return super(CrunchyrollBaseIE, self)._download_webpage(
request, video_id, note, errnote, fatal, tries, timeout, encoding)
@staticmethod
def _add_skip_wall(url):
parsed_url = compat_urlparse.urlparse(url)
qs = compat_urlparse.parse_qs(parsed_url.query)
# Always force skip_wall to bypass maturity wall, namely 18+ confirmation message:
# > This content may be inappropriate for some people.
# > Are you sure you want to continue?
# since it's not disabled by default in crunchyroll account's settings.
# See https://github.com/rg3/youtube-dl/issues/7202.
qs['skip_wall'] = ['1']
return compat_urlparse.urlunparse(
parsed_url._replace(query=compat_urllib_parse.urlencode(qs, True)))
class CrunchyrollIE(CrunchyrollBaseIE):
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
_NETRC_MACHINE = 'crunchyroll'
_TESTS = [{
'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
'info_dict': {
@ -72,7 +105,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
'id': '589804',
'ext': 'flv',
'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11',
'description': 'md5:fe2743efedb49d279552926d0bd0cd9e',
'description': 'md5:2fbc01f90b87e8e9137296f37b461c12',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': 'Danny Choo Network',
'upload_date': '20120213',
@ -81,10 +114,13 @@ class CrunchyrollIE(CrunchyrollBaseIE):
# rtmp
'skip_download': True,
},
}, {
'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
'only_matching': True,
}, {
# geo-restricted (US), 18+ maturity wall, non-premium available
'url': 'http://www.crunchyroll.com/cosplay-complex-ova/episode-1-the-birth-of-the-cosplay-club-565617',
'only_matching': True,
}]
_FORMAT_IDS = {
@ -94,24 +130,6 @@ class CrunchyrollIE(CrunchyrollBaseIE):
'1080': ('80', '108'),
}
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
self.report_login()
login_url = 'https://www.crunchyroll.com/?a=formhandler'
data = urlencode_postdata({
'formname': 'RpcApiUser_Login',
'name': username,
'password': password,
})
login_request = compat_urllib_request.Request(login_url, data)
login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
self._download_webpage(login_request, None, False, 'Wrong login info')
def _real_initialize(self):
self._login()
def _decrypt_subtitles(self, data, iv, id):
data = bytes_to_intlist(base64.b64decode(data.encode('utf-8')))
iv = bytes_to_intlist(base64.b64decode(iv.encode('utf-8')))
@ -217,7 +235,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
return output
def _extract_subtitles(self, subtitle):
sub_root = xml.etree.ElementTree.fromstring(subtitle)
sub_root = compat_etree_fromstring(subtitle)
return [{
'ext': 'srt',
'data': self._convert_subtitles_to_srt(sub_root),
@ -228,7 +246,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
def _get_subtitles(self, video_id, webpage):
subtitles = {}
for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage):
for sub_id, sub_name in re.findall(r'\bssid=([0-9]+)"[^>]+?\btitle="([^"]+)', webpage):
sub_page = self._download_webpage(
'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id=' + sub_id,
video_id, note='Downloading subtitles for ' + sub_name)
@ -254,7 +272,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
else:
webpage_url = 'http://www.' + mobj.group('url')
webpage = self._download_webpage(webpage_url, video_id, 'Downloading webpage')
webpage = self._download_webpage(self._add_skip_wall(webpage_url), video_id, 'Downloading webpage')
note_m = self._html_search_regex(
r'<div class="showmedia-trailer-notice">(.+?)</div>',
webpage, 'trailer-notice', default='')
@ -270,11 +288,15 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
if 'To view this, please log in to verify you are 18 or older.' in webpage:
self.raise_login_required()
video_title = self._html_search_regex(r'<h1[^>]*>(.+?)</h1>', webpage, 'video_title', flags=re.DOTALL)
video_title = self._html_search_regex(
r'(?s)<h1[^>]*>((?:(?!<h1).)*?<span[^>]+itemprop=["\']title["\'][^>]*>(?:(?!<h1).)+?)</h1>',
webpage, 'video_title')
video_title = re.sub(r' {2,}', ' ', video_title)
video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='')
if not video_description:
video_description = None
video_description = self._html_search_regex(
r'<script[^>]*>\s*.+?\[media_id=%s\].+?"description"\s*:\s*"([^"]+)' % video_id,
webpage, 'description', default=None)
if video_description:
video_description = lowercase_escape(video_description.replace(r'\r\n', '\n'))
video_upload_date = self._html_search_regex(
[r'<div>Availability for free users:(.+?)</div>', r'<div>[^<>]+<span>\s*(.+?\d{4})\s*</span></div>'],
webpage, 'video_upload_date', fatal=False, flags=re.DOTALL)
@ -352,7 +374,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
IE_NAME = "crunchyroll:playlist"
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<id>[\w\-]+))/?$'
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<id>[\w\-]+))/?(?:\?|$)'
_TESTS = [{
'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
@ -361,12 +383,25 @@ class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
'title': 'A Bridge to the Starry Skies - Hoshizora e Kakaru Hashi'
},
'playlist_count': 13,
}, {
# geo-restricted (US), 18+ maturity wall, non-premium available
'url': 'http://www.crunchyroll.com/cosplay-complex-ova',
'info_dict': {
'id': 'cosplay-complex-ova',
'title': 'Cosplay Complex OVA'
},
'playlist_count': 3,
'skip': 'Georestricted',
}, {
# geo-restricted (US), 18+ maturity wall, non-premium will be available since 2015.11.14
'url': 'http://www.crunchyroll.com/ladies-versus-butlers?skip_wall=1',
'only_matching': True,
}]
def _real_extract(self, url):
show_id = self._match_id(url)
webpage = self._download_webpage(url, show_id)
webpage = self._download_webpage(self._add_skip_wall(url), show_id)
title = self._html_search_regex(
r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
webpage, 'title')

31
youtube_dl/extractor/dailymotion.py
View File

@ -96,6 +96,11 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'uploader': 'HotWaves1012',
'age_limit': 18,
}
},
# geo-restricted, player v5
{
'url': 'http://www.dailymotion.com/video/xhza0o',
'only_matching': True,
}
]
@ -124,6 +129,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
if player_v5:
player = self._parse_json(player_v5, video_id)
metadata = player['metadata']
self._check_error(metadata)
formats = []
for quality, media_list in metadata['qualities'].items():
for media in media_list:
@ -133,9 +141,17 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
type_ = media.get('type')
if type_ == 'application/vnd.lumberjack.manifest':
continue
if type_ == 'application/x-mpegURL' or determine_ext(media_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
media_url, video_id, 'mp4', m3u8_id='hls'))
ext = determine_ext(media_url)
if type_ == 'application/x-mpegURL' or ext == 'm3u8':
m3u8_formats = self._extract_m3u8_formats(
media_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
if m3u8_formats:
formats.extend(m3u8_formats)
elif type_ == 'application/f4m' or ext == 'f4m':
f4m_formats = self._extract_f4m_formats(
media_url, video_id, preference=-1, f4m_id='hds', fatal=False)
if f4m_formats:
formats.extend(f4m_formats)
else:
f = {
'url': media_url,
@ -201,9 +217,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'video info', flags=re.MULTILINE),
video_id)
if info.get('error') is not None:
msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title']
raise ExtractorError(msg, expected=True)
self._check_error(info)
formats = []
for (key, format_id) in self._FORMATS:
@ -246,6 +260,11 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'duration': info['duration']
}
def _check_error(self, info):
if info.get('error') is not None:
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, info['error']['title']), expected=True)
def _get_subtitles(self, video_id, webpage):
try:
sub_list = self._download_webpage(

88
youtube_dl/extractor/democracynow.py Normal file
View File

@ -0,0 +1,88 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import os.path
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
url_basename,
remove_start,
)
class DemocracynowIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?democracynow.org/(?P<id>[^\?]*)'
IE_NAME = 'democracynow'
_TESTS = [{
'url': 'http://www.democracynow.org/shows/2015/7/3',
'md5': 'fbb8fe3d7a56a5e12431ce2f9b2fab0d',
'info_dict': {
'id': '2015-0703-001',
'ext': 'mp4',
'title': 'July 03, 2015 - Democracy Now!',
'description': 'A daily independent global news hour with Amy Goodman & Juan González "What to the Slave is 4th of July?": James Earl Jones Reads Frederick Douglass\u2019 Historic Speech : "This Flag Comes Down Today": Bree Newsome Scales SC Capitol Flagpole, Takes Down Confederate Flag : "We Shall Overcome": Remembering Folk Icon, Activist Pete Seeger in His Own Words & Songs',
},
}, {
'url': 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree',
'md5': 'fbb8fe3d7a56a5e12431ce2f9b2fab0d',
'info_dict': {
'id': '2015-0703-001',
'ext': 'mp4',
'title': '"This Flag Comes Down Today": Bree Newsome Scales SC Capitol Flagpole, Takes Down Confederate Flag',
'description': 'md5:4d2bc4f0d29f5553c2210a4bc7761a21',
},
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
description = self._og_search_description(webpage)
json_data = self._parse_json(self._search_regex(
r'<script[^>]+type="text/json"[^>]*>\s*({[^>]+})', webpage, 'json'),
display_id)
video_id = None
formats = []
default_lang = 'en'
subtitles = {}
def add_subtitle_item(lang, info_dict):
if lang not in subtitles:
subtitles[lang] = []
subtitles[lang].append(info_dict)
# chapter_file are not subtitles
if 'caption_file' in json_data:
add_subtitle_item(default_lang, {
'url': compat_urlparse.urljoin(url, json_data['caption_file']),
})
for subtitle_item in json_data.get('captions', []):
lang = subtitle_item.get('language', '').lower() or default_lang
add_subtitle_item(lang, {
'url': compat_urlparse.urljoin(url, subtitle_item['url']),
})
for key in ('file', 'audio', 'video'):
media_url = json_data.get(key, '')
if not media_url:
continue
media_url = re.sub(r'\?.*', '', compat_urlparse.urljoin(url, media_url))
video_id = video_id or remove_start(os.path.splitext(url_basename(media_url))[0], 'dn')
formats.append({
'url': media_url,
})
self._sort_formats(formats)
return {
'id': video_id or display_id,
'title': json_data['title'],
'description': description,
'subtitles': subtitles,
'formats': formats,
}

2
youtube_dl/extractor/eagleplatform.py
View File

@ -87,7 +87,7 @@ class EaglePlatformIE(InfoExtractor):
m3u8_url = self._get_video_url(secure_m3u8, video_id, 'Downloading m3u8 JSON')
formats = self._extract_m3u8_formats(
m3u8_url, video_id,
'mp4', entry_protocol='m3u8_native')
'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
mp4_url = self._get_video_url(
# Secure mp4 URL is constructed according to Player.prototype.mp4 from

95
youtube_dl/extractor/eitb.py
View File

@ -1,39 +1,92 @@
# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .brightcove import BrightcoveIE
from ..utils import ExtractorError
from ..compat import compat_urllib_request
from ..utils import (
float_or_none,
int_or_none,
parse_iso8601,
)
class EitbIE(InfoExtractor):
IE_NAME = 'eitb.tv'
_VALID_URL = r'https?://www\.eitb\.tv/(eu/bideoa|es/video)/[^/]+/(?P<playlist_id>\d+)/(?P<chapter_id>\d+)'
_VALID_URL = r'https?://(?:www\.)?eitb\.tv/(?:eu/bideoa|es/video)/[^/]+/\d+/(?P<id>\d+)'
_TEST = {
'add_ie': ['Brightcove'],
'url': 'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/2677100210001/2743577154001/lasa-y-zabala-30-anos/',
'url': 'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/4104995148001/4090227752001/lasa-y-zabala-30-anos/',
'md5': 'edf4436247185adee3ea18ce64c47998',
'info_dict': {
'id': '2743577154001',
'id': '4090227752001',
'ext': 'mp4',
'title': '60 minutos (Lasa y Zabala, 30 años)',
# All videos from eitb has this description in the brightcove info
'description': '.',
'uploader': 'Euskal Telebista',
'description': 'Programa de reportajes de actualidad.',
'duration': 3996.76,
'timestamp': 1381789200,
'upload_date': '20131014',
'tags': list,
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
chapter_id = mobj.group('chapter_id')
webpage = self._download_webpage(url, chapter_id)
bc_url = BrightcoveIE._extract_brightcove_url(webpage)
if bc_url is None:
raise ExtractorError('Could not extract the Brightcove url')
# The BrightcoveExperience object doesn't contain the video id, we set
# it manually
bc_url += '&%40videoPlayer={0}'.format(chapter_id)
return self.url_result(bc_url, BrightcoveIE.ie_key())
video_id = self._match_id(url)
video = self._download_json(
'http://mam.eitb.eus/mam/REST/ServiceMultiweb/Video/MULTIWEBTV/%s/' % video_id,
video_id, 'Downloading video JSON')
media = video['web_media'][0]
formats = []
for rendition in media['RENDITIONS']:
video_url = rendition.get('PMD_URL')
if not video_url:
continue
tbr = float_or_none(rendition.get('ENCODING_RATE'), 1000)
format_id = 'http'
if tbr:
format_id += '-%d' % int(tbr)
formats.append({
'url': rendition['PMD_URL'],
'format_id': format_id,
'width': int_or_none(rendition.get('FRAME_WIDTH')),
'height': int_or_none(rendition.get('FRAME_HEIGHT')),
'tbr': tbr,
})
hls_url = media.get('HLS_SURL')
if hls_url:
request = compat_urllib_request.Request(
'http://mam.eitb.eus/mam/REST/ServiceMultiweb/DomainRestrictedSecurity/TokenAuth/',
headers={'Referer': url})
token_data = self._download_json(
request, video_id, 'Downloading auth token', fatal=False)
if token_data:
token = token_data.get('token')
if token:
m3u8_formats = self._extract_m3u8_formats(
'%s?hdnts=%s' % (hls_url, token), video_id, m3u8_id='hls', fatal=False)
if m3u8_formats:
formats.extend(m3u8_formats)
hds_url = media.get('HDS_SURL')
if hds_url:
f4m_formats = self._extract_f4m_formats(
'%s?hdcore=3.7.0' % hds_url.replace('euskalsvod', 'euskalvod'),
video_id, f4m_id='hds', fatal=False)
if f4m_formats:
formats.extend(f4m_formats)
self._sort_formats(formats)
return {
'id': video_id,
'title': media.get('NAME_ES') or media.get('name') or media['NAME_EU'],
'description': media.get('SHORT_DESC_ES') or video.get('desc_group') or media.get('SHORT_DESC_EU'),
'thumbnail': media.get('STILL_URL') or media.get('THUMBNAIL_URL'),
'duration': float_or_none(media.get('LENGTH'), 1000),
'timestamp': parse_iso8601(media.get('BROADCST_DATE'), ' '),
'tags': media.get('TAGS'),
'formats': formats,
}

59
youtube_dl/extractor/extremetube.py
View File

@ -3,23 +3,20 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_request,
)
from ..compat import compat_urllib_request
from ..utils import (
qualities,
int_or_none,
str_to_int,
)
class ExtremeTubeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<id>[0-9]+))(?:[/?&]|$)'
_VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?P<id>[^/#?&]+)'
_TESTS = [{
'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
'md5': '344d0c6d50e2f16b06e49ca011d8ac69',
'info_dict': {
'id': '652431',
'id': 'music-video-14-british-euro-brit-european-cumshots-swallow-652431',
'ext': 'mp4',
'title': 'Music Video 14 british euro brit european cumshots swallow',
'uploader': 'unknown',
@ -29,12 +26,16 @@ class ExtremeTubeIE(InfoExtractor):
}, {
'url': 'http://www.extremetube.com/gay/video/abcde-1234',
'only_matching': True,
}, {
'url': 'http://www.extremetube.com/video/latina-slut-fucked-by-fat-black-dick',
'only_matching': True,
}, {
'url': 'http://www.extremetube.com/video/652431',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
url = 'http://www.' + mobj.group('url')
video_id = self._match_id(url)
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
@ -49,20 +50,36 @@ class ExtremeTubeIE(InfoExtractor):
r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
webpage, 'view count', fatal=False))
flash_vars = compat_parse_qs(self._search_regex(
r'<param[^>]+?name="flashvars"[^>]+?value="([^"]+)"', webpage, 'flash vars'))
flash_vars = self._parse_json(
self._search_regex(
r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flash vars'),
video_id)
formats = []
quality = qualities(['180p', '240p', '360p', '480p', '720p', '1080p'])
for k, vals in flash_vars.items():
m = re.match(r'quality_(?P<quality>[0-9]+p)$', k)
if m is not None:
formats.append({
'format_id': m.group('quality'),
'quality': quality(m.group('quality')),
'url': vals[0],
for quality_key, video_url in flash_vars.items():
height = int_or_none(self._search_regex(
r'quality_(\d+)[pP]$', quality_key, 'height', default=None))
if not height:
continue
f = {
'url': video_url,
}
mobj = re.search(
r'/(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url)
if mobj:
height = int(mobj.group('height'))
bitrate = int(mobj.group('bitrate'))
f.update({
'format_id': '%dp-%dk' % (height, bitrate),
'height': height,
'tbr': bitrate,
})
else:
f.update({
'format_id': '%dp' % height,
'height': height,
})
formats.append(f)
self._sort_formats(formats)
return {

23
youtube_dl/extractor/facebook.py
View File

@ -14,7 +14,6 @@ from ..compat import (
)
from ..utils import (
ExtractorError,
int_or_none,
limit_length,
urlencode_postdata,
get_element_by_id,
@ -142,16 +141,20 @@ class FacebookIE(InfoExtractor):
data = dict(json.loads(m.group(1)))
params_raw = compat_urllib_parse_unquote(data['params'])
params = json.loads(params_raw)
video_data = params['video_data'][0]
formats = []
for quality in ['sd', 'hd']:
src = video_data.get('%s_src' % quality)
if src is not None:
formats.append({
'format_id': quality,
'url': src,
})
for format_id, f in params['video_data'].items():
if not f or not isinstance(f, list):
continue
for quality in ('sd', 'hd'):
for src_type in ('src', 'src_no_ratelimit'):
src = f[0].get('%s_%s' % (quality, src_type))
if src:
formats.append({
'format_id': '%s_%s_%s' % (format_id, quality, src_type),
'url': src,
'preference': -10 if format_id == 'progressive' else 0,
})
if not formats:
raise ExtractorError('Cannot find video formats')
@ -171,7 +174,5 @@ class FacebookIE(InfoExtractor):
'id': video_id,
'title': video_title,
'formats': formats,
'duration': int_or_none(video_data.get('video_duration')),
'thumbnail': video_data.get('thumbnail_src'),
'uploader': uploader,
}

28
youtube_dl/extractor/francetv.py
View File

@ -83,6 +83,14 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
if subtitle:
title += ' - %s' % subtitle
subtitles = {}
subtitles_list = [{
'url': subformat['url'],
'ext': subformat.get('format'),
} for subformat in info.get('subtitles', []) if subformat.get('url')]
if subtitles_list:
subtitles['fr'] = subtitles_list
return {
'id': video_id,
'title': title,
@ -91,20 +99,27 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
'duration': int_or_none(info.get('real_duration')) or parse_duration(info['duree']),
'timestamp': int_or_none(info['diffusion']['timestamp']),
'formats': formats,
'subtitles': subtitles,
}
class PluzzIE(FranceTVBaseInfoExtractor):
IE_NAME = 'pluzz.francetv.fr'
_VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'
_VALID_URL = r'https?://(?:m\.)?pluzz\.francetv\.fr/videos/(?P<id>.+?)\.html'
# Can't use tests, videos expire in 7 days
def _real_extract(self, url):
title = re.match(self._VALID_URL, url).group(1)
webpage = self._download_webpage(url, title)
video_id = self._search_regex(
r'data-diffusion="(\d+)"', webpage, 'ID')
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._html_search_meta(
'id_video', webpage, 'video id', default=None)
if not video_id:
video_id = self._search_regex(
r'data-diffusion=["\'](\d+)', webpage, 'video id')
return self._extract_video(video_id, 'Pluzz')
@ -120,6 +135,9 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
'title': 'Soir 3',
'upload_date': '20130826',
'timestamp': 1377548400,
'subtitles': {
'fr': 'mincount:2',
},
},
}, {
'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',

5
youtube_dl/extractor/generic.py
View File

@ -9,6 +9,7 @@ import sys
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..compat import (
compat_etree_fromstring,
compat_urllib_parse_unquote,
compat_urllib_request,
compat_urlparse,
@ -21,7 +22,6 @@ from ..utils import (
HEADRequest,
is_html,
orderedSet,
parse_xml,
smuggle_url,
unescapeHTML,
unified_strdate,
@ -141,6 +141,7 @@ class GenericIE(InfoExtractor):
'ext': 'mp4',
'title': 'Automatics, robotics and biocybernetics',
'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
'upload_date': '20130627',
'formats': 'mincount:16',
'subtitles': 'mincount:1',
},
@ -1237,7 +1238,7 @@ class GenericIE(InfoExtractor):
# Is it an RSS feed, a SMIL file or a XSPF playlist?
try:
doc = parse_xml(webpage)
doc = compat_etree_fromstring(webpage.encode('utf-8'))
if doc.tag == 'rss':
return self._extract_rss(url, video_id, doc)
elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):

159
youtube_dl/extractor/globo.py
View File

@ -14,79 +14,58 @@ from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
str_or_none,
)
class GloboIE(InfoExtractor):
_VALID_URL = 'https?://.+?\.globo\.com/(?P<id>.+)'
_VALID_URL = '(?:globo:|https?://.+?\.globo\.com/(?:[^/]+/)*(?:v/(?:[^/]+/)?|videos/))(?P<id>\d{7,})'
_API_URL_TEMPLATE = 'http://api.globovideos.com/videos/%s/playlist'
_SECURITY_URL_TEMPLATE = 'http://security.video.globo.com/videos/%s/hash?player=flash&version=17.0.0.132&resource_id=%s'
_VIDEOID_REGEXES = [
r'\bdata-video-id="(\d+)"',
r'\bdata-player-videosids="(\d+)"',
r'<div[^>]+\bid="(\d+)"',
]
_RESIGN_EXPIRATION = 86400
_TESTS = [
{
'url': 'http://globotv.globo.com/sportv/futebol-nacional/v/os-gols-de-atletico-mg-3-x-2-santos-pela-24a-rodada-do-brasileirao/3654973/',
'md5': '03ebf41cb7ade43581608b7d9b71fab0',
'info_dict': {
'id': '3654973',
'ext': 'mp4',
'title': 'Os gols de Atlético-MG 3 x 2 Santos pela 24ª rodada do Brasileirão',
'duration': 251.585,
'uploader': 'SporTV',
'uploader_id': 698,
'like_count': int,
}
_TESTS = [{
'url': 'http://g1.globo.com/carros/autoesporte/videos/t/exclusivos-do-g1/v/mercedes-benz-gla-passa-por-teste-de-colisao-na-europa/3607726/',
'md5': 'b3ccc801f75cd04a914d51dadb83a78d',
'info_dict': {
'id': '3607726',
'ext': 'mp4',
'title': 'Mercedes-Benz GLA passa por teste de colisão na Europa',
'duration': 103.204,
'uploader': 'Globo.com',
'uploader_id': '265',
},
{
'url': 'http://g1.globo.com/carros/autoesporte/videos/t/exclusivos-do-g1/v/mercedes-benz-gla-passa-por-teste-de-colisao-na-europa/3607726/',
'md5': 'b3ccc801f75cd04a914d51dadb83a78d',
'info_dict': {
'id': '3607726',
'ext': 'mp4',
'title': 'Mercedes-Benz GLA passa por teste de colisão na Europa',
'duration': 103.204,
'uploader': 'Globo.com',
'uploader_id': 265,
'like_count': int,
}
}, {
'url': 'http://globoplay.globo.com/v/4581987/',
'md5': 'f36a1ecd6a50da1577eee6dd17f67eff',
'info_dict': {
'id': '4581987',
'ext': 'mp4',
'title': 'Acidentes de trânsito estão entre as maiores causas de queda de energia em SP',
'duration': 137.973,
'uploader': 'Rede Globo',
'uploader_id': '196',
},
{
'url': 'http://g1.globo.com/jornal-nacional/noticia/2014/09/novidade-na-fiscalizacao-de-bagagem-pela-receita-provoca-discussoes.html',
'md5': '307fdeae4390ccfe6ba1aa198cf6e72b',
'info_dict': {
'id': '3652183',
'ext': 'mp4',
'title': 'Receita Federal explica como vai fiscalizar bagagens de quem retorna ao Brasil de avião',
'duration': 110.711,
'uploader': 'Rede Globo',
'uploader_id': 196,
'like_count': int,
}
},
{
'url': 'http://globotv.globo.com/canal-brasil/sangue-latino/t/todos-os-videos/v/ator-e-diretor-argentino-ricado-darin-fala-sobre-utopias-e-suas-perdas/3928201/',
'md5': 'c1defca721ce25b2354e927d3e4b3dec',
'info_dict': {
'id': '3928201',
'ext': 'mp4',
'title': 'Ator e diretor argentino, Ricado Darín fala sobre utopias e suas perdas',
'duration': 1472.906,
'uploader': 'Canal Brasil',
'uploader_id': 705,
'like_count': int,
}
},
]
}, {
'url': 'http://canalbrasil.globo.com/programas/sangue-latino/videos/3928201.html',
'only_matching': True,
}, {
'url': 'http://globosatplay.globo.com/globonews/v/4472924/',
'only_matching': True,
}, {
'url': 'http://globotv.globo.com/t/programa/v/clipe-sexo-e-as-negas-adeus/3836166/',
'only_matching': True,
}, {
'url': 'http://globotv.globo.com/canal-brasil/sangue-latino/t/todos-os-videos/v/ator-e-diretor-argentino-ricado-darin-fala-sobre-utopias-e-suas-perdas/3928201/',
'only_matching': True,
}, {
'url': 'http://canaloff.globo.com/programas/desejar-profundo/videos/4518560.html',
'only_matching': True,
}]
class MD5():
class MD5:
HEX_FORMAT_LOWERCASE = 0
HEX_FORMAT_UPPERCASE = 1
BASE64_PAD_CHARACTER_DEFAULT_COMPLIANCE = ''
@ -353,9 +332,6 @@ class GloboIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_id = self._search_regex(self._VIDEOID_REGEXES, webpage, 'video id')
video = self._download_json(
self._API_URL_TEMPLATE % video_id, video_id)['videos'][0]
@ -364,7 +340,7 @@ class GloboIE(InfoExtractor):
formats = []
for resource in video['resources']:
resource_id = resource.get('_id')
if not resource_id:
if not resource_id or resource_id.endswith('manifest'):
continue
security = self._download_json(
@ -393,20 +369,23 @@ class GloboIE(InfoExtractor):
resource_url = resource['url']
signed_url = '%s?h=%s&k=%s' % (resource_url, signed_hash, 'flash')
if resource_id.endswith('m3u8') or resource_url.endswith('.m3u8'):
formats.extend(self._extract_m3u8_formats(signed_url, resource_id, 'mp4'))
m3u8_formats = self._extract_m3u8_formats(
signed_url, resource_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False)
if m3u8_formats:
formats.extend(m3u8_formats)
else:
formats.append({
'url': signed_url,
'format_id': resource_id,
'height': resource.get('height'),
'format_id': 'http-%s' % resource_id,
'height': int_or_none(resource.get('height')),
})
self._sort_formats(formats)
duration = float_or_none(video.get('duration'), 1000)
like_count = int_or_none(video.get('likes'))
uploader = video.get('channel')
uploader_id = video.get('channel_id')
uploader_id = str_or_none(video.get('channel_id'))
return {
'id': video_id,
@ -414,6 +393,46 @@ class GloboIE(InfoExtractor):
'duration': duration,
'uploader': uploader,
'uploader_id': uploader_id,
'like_count': like_count,
'formats': formats
}
class GloboArticleIE(InfoExtractor):
_VALID_URL = 'https?://.+?\.globo\.com/(?:[^/]+/)*(?P<id>[^/]+)\.html'
_VIDEOID_REGEXES = [
r'\bdata-video-id=["\'](\d{7,})',
r'\bdata-player-videosids=["\'](\d{7,})',
r'\bvideosIDs\s*:\s*["\'](\d{7,})',
r'\bdata-id=["\'](\d{7,})',
r'<div[^>]+\bid=["\'](\d{7,})',
]
_TESTS = [{
'url': 'http://g1.globo.com/jornal-nacional/noticia/2014/09/novidade-na-fiscalizacao-de-bagagem-pela-receita-provoca-discussoes.html',
'md5': '307fdeae4390ccfe6ba1aa198cf6e72b',
'info_dict': {
'id': '3652183',
'ext': 'mp4',
'title': 'Receita Federal explica como vai fiscalizar bagagens de quem retorna ao Brasil de avião',
'duration': 110.711,
'uploader': 'Rede Globo',
'uploader_id': '196',
}
}, {
'url': 'http://gq.globo.com/Prazeres/Poder/noticia/2015/10/all-o-desafio-assista-ao-segundo-capitulo-da-serie.html',
'only_matching': True,
}, {
'url': 'http://gshow.globo.com/programas/tv-xuxa/O-Programa/noticia/2014/01/xuxa-e-junno-namoram-muuuito-em-luau-de-zeze-di-camargo-e-luciano.html',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if GloboIE.suitable(url) else super(GloboArticleIE, cls).suitable(url)
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(self._VIDEOID_REGEXES, webpage, 'video id')
return self.url_result('globo:%s' % video_id, 'Globo')

2
youtube_dl/extractor/googleplus.py
View File

@ -61,7 +61,7 @@ class GooglePlusIE(InfoExtractor):
'width': int(width),
'height': int(height),
} for width, height, video_url in re.findall(
r'\d+,(\d+),(\d+),"(https?://redirector\.googlevideo\.com.*?)"', webpage)]
r'\d+,(\d+),(\d+),"(https?://[^.]+\.googleusercontent.com.*?)"', webpage)]
self._sort_formats(formats)
return {

29
youtube_dl/extractor/imdb.py
View File

@ -4,8 +4,8 @@ import re
import json
from .common import InfoExtractor
from ..compat import (
compat_urlparse,
from ..utils import (
qualities,
)
@ -30,24 +30,33 @@ class ImdbIE(InfoExtractor):
descr = self._html_search_regex(
r'(?s)<span itemprop="description">(.*?)</span>',
webpage, 'description', fatal=False)
available_formats = re.findall(
r'case \'(?P<f_id>.*?)\' :$\s+url = \'(?P<path>.*?)\'', webpage,
flags=re.MULTILINE)
player_url = 'http://www.imdb.com/video/imdb/vi%s/imdb/single' % video_id
player_page = self._download_webpage(
player_url, video_id, 'Downloading player page')
# the player page contains the info for the default format, we have to
# fetch other pages for the rest of the formats
extra_formats = re.findall(r'href="(?P<url>%s.*?)".*?>(?P<name>.*?)<' % re.escape(player_url), player_page)
format_pages = [
self._download_webpage(
f_url, video_id, 'Downloading info for %s format' % f_name)
for f_url, f_name in extra_formats]
format_pages.append(player_page)
quality = qualities(['SD', '480p', '720p'])
formats = []
for f_id, f_path in available_formats:
f_path = f_path.strip()
format_page = self._download_webpage(
compat_urlparse.urljoin(url, f_path),
'Downloading info for %s format' % f_id)
for format_page in format_pages:
json_data = self._search_regex(
r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
format_page, 'json data', flags=re.DOTALL)
info = json.loads(json_data)
format_info = info['videoPlayerObject']['video']
f_id = format_info['ffname']
formats.append({
'format_id': f_id,
'url': format_info['videoInfoList'][0]['videoUrl'],
'quality': quality(f_id),
})
self._sort_formats(formats)
return {
'id': video_id,

6
youtube_dl/extractor/iqiyi.py
View File

@ -205,9 +205,9 @@ class IqiyiIE(InfoExtractor):
def get_enc_key(self, swf_url, video_id):
# TODO: automatic key extraction
# last update at 2015-10-10 for Zombie::bite
# '7239670519b6ac209a0bee4ef0446a6b24894b8ac2751506e42116212a0d0272e505'[2:66][1::2]
enc_key = '97596c0abee04ab49ba25564161ad225'
# last update at 2015-10-22 for Zombie::bite
# '7223c67061dbea1259d0ceb44f44b6d62288f4f80c972170de5201d2321060270e05'[2:66][0::2]
enc_key = '2c76de15dcb44bd28ff0927d50d31620'
return enc_key
def _real_extract(self, url):

70
youtube_dl/extractor/letv.py
View File

@ -9,13 +9,14 @@ from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
compat_urlparse,
compat_ord,
)
from ..utils import (
determine_ext,
ExtractorError,
parse_iso8601,
int_or_none,
encode_data_uri,
)
@ -25,15 +26,16 @@ class LetvIE(InfoExtractor):
_TESTS = [{
'url': 'http://www.letv.com/ptv/vplay/22005890.html',
'md5': 'cab23bd68d5a8db9be31c9a222c1e8df',
'md5': 'edadcfe5406976f42f9f266057ee5e40',
'info_dict': {
'id': '22005890',
'ext': 'mp4',
'title': '第87届奥斯卡颁奖礼完美落幕 《鸟人》成最大赢家',
'timestamp': 1424747397,
'upload_date': '20150224',
'description': 'md5:a9cb175fd753e2962176b7beca21a47c',
}
},
'params': {
'hls_prefer_native': True,
},
}, {
'url': 'http://www.letv.com/ptv/vplay/1415246.html',
'info_dict': {
@ -42,16 +44,22 @@ class LetvIE(InfoExtractor):
'title': '美人天下01',
'description': 'md5:f88573d9d7225ada1359eaf0dbf8bcda',
},
'params': {
'hls_prefer_native': True,
},
}, {
'note': 'This video is available only in Mainland China, thus a proxy is needed',
'url': 'http://www.letv.com/ptv/vplay/1118082.html',
'md5': 'f80936fbe20fb2f58648e81386ff7927',
'md5': '2424c74948a62e5f31988438979c5ad1',
'info_dict': {
'id': '1118082',
'ext': 'mp4',
'title': '与龙共舞 完整版',
'description': 'md5:7506a5eeb1722bb9d4068f85024e3986',
},
'params': {
'hls_prefer_native': True,
},
'skip': 'Only available in China',
}]
@ -74,6 +82,27 @@ class LetvIE(InfoExtractor):
_loc3_ = self.ror(_loc3_, _loc2_ % 17)
return _loc3_
# see M3U8Encryption class in KLetvPlayer.swf
@staticmethod
def decrypt_m3u8(encrypted_data):
if encrypted_data[:5].decode('utf-8').lower() != 'vc_01':
return encrypted_data
encrypted_data = encrypted_data[5:]
_loc4_ = bytearray()
while encrypted_data:
b = compat_ord(encrypted_data[0])
_loc4_.extend([b // 16, b & 0x0f])
encrypted_data = encrypted_data[1:]
idx = len(_loc4_) - 11
_loc4_ = _loc4_[idx:] + _loc4_[:idx]
_loc7_ = bytearray()
while _loc4_:
_loc7_.append(_loc4_[0] * 16 + _loc4_[1])
_loc4_ = _loc4_[2:]
return bytes(_loc7_)
def _real_extract(self, url):
media_id = self._match_id(url)
page = self._download_webpage(url, media_id)
@ -115,23 +144,28 @@ class LetvIE(InfoExtractor):
for format_id in formats:
if format_id in dispatch:
media_url = playurl['domain'][0] + dispatch[format_id][0]
# Mimic what flvxz.com do
url_parts = list(compat_urlparse.urlparse(media_url))
qs = dict(compat_urlparse.parse_qs(url_parts[4]))
qs.update({
'platid': '14',
'splatid': '1401',
'tss': 'no',
'retry': 1
media_url += '&' + compat_urllib_parse.urlencode({
'm3v': 1,
'format': 1,
'expect': 3,
'rateid': format_id,
})
url_parts[4] = compat_urllib_parse.urlencode(qs)
media_url = compat_urlparse.urlunparse(url_parts)
nodes_data = self._download_json(
media_url, media_id,
'Download JSON metadata for format %s' % format_id)
req = self._request_webpage(
nodes_data['nodelist'][0]['location'], media_id,
note='Downloading m3u8 information for format %s' % format_id)
m3u8_data = self.decrypt_m3u8(req.read())
url_info_dict = {
'url': media_url,
'url': encode_data_uri(m3u8_data, 'application/vnd.apple.mpegurl'),
'ext': determine_ext(dispatch[format_id][1]),
'format_id': format_id,
'protocol': 'm3u8',
}
if format_id[-1:] == 'p':

72
youtube_dl/extractor/lynda.py
View File

@ -82,6 +82,11 @@ class LyndaBaseIE(InfoExtractor):
expected=True)
raise ExtractorError('Unable to log in')
def _logout(self):
self._download_webpage(
'http://www.lynda.com/ajax/logout.aspx', None,
'Logging out', 'Unable to log out', fatal=False)
class LyndaIE(LyndaBaseIE):
IE_NAME = 'lynda'
@ -108,50 +113,47 @@ class LyndaIE(LyndaBaseIE):
def _real_extract(self, url):
video_id = self._match_id(url)
page = self._download_webpage(
video = self._download_json(
'http://www.lynda.com/ajax/player?videoId=%s&type=video' % video_id,
video_id, 'Downloading video JSON')
video_json = json.loads(page)
if 'Status' in video_json:
if 'Status' in video:
raise ExtractorError(
'lynda returned error: %s' % video_json['Message'], expected=True)
'lynda returned error: %s' % video['Message'], expected=True)
if video_json['HasAccess'] is False:
if video.get('HasAccess') is False:
self.raise_login_required('Video %s is only available for members' % video_id)
video_id = compat_str(video_json['ID'])
duration = video_json['DurationInSeconds']
title = video_json['Title']
video_id = compat_str(video.get('ID') or video_id)
duration = int_or_none(video.get('DurationInSeconds'))
title = video['Title']
formats = []
fmts = video_json.get('Formats')
fmts = video.get('Formats')
if fmts:
formats.extend([
{
'url': fmt['Url'],
'ext': fmt['Extension'],
'width': fmt['Width'],
'height': fmt['Height'],
'filesize': fmt['FileSize'],
'format_id': str(fmt['Resolution'])
} for fmt in fmts])
formats.extend([{
'url': f['Url'],
'ext': f.get('Extension'),
'width': int_or_none(f.get('Width')),
'height': int_or_none(f.get('Height')),
'filesize': int_or_none(f.get('FileSize')),
'format_id': compat_str(f.get('Resolution')) if f.get('Resolution') else None,
} for f in fmts if f.get('Url')])
prioritized_streams = video_json.get('PrioritizedStreams')
prioritized_streams = video.get('PrioritizedStreams')
if prioritized_streams:
formats.extend([
{
for prioritized_stream_id, prioritized_stream in prioritized_streams.items():
formats.extend([{
'url': video_url,
'width': int_or_none(format_id),
'format_id': format_id,
} for format_id, video_url in prioritized_streams['0'].items()
])
'format_id': '%s-%s' % (prioritized_stream_id, format_id),
} for format_id, video_url in prioritized_stream.items()])
self._check_formats(formats, video_id)
self._sort_formats(formats)
subtitles = self.extract_subtitles(video_id, page)
subtitles = self.extract_subtitles(video_id)
return {
'id': video_id,
@ -182,7 +184,7 @@ class LyndaIE(LyndaBaseIE):
if srt:
return srt
def _get_subtitles(self, video_id, webpage):
def _get_subtitles(self, video_id):
url = 'http://www.lynda.com/ajax/player?videoId=%s&type=transcript' % video_id
subs = self._download_json(url, None, False)
if subs:
@ -204,12 +206,13 @@ class LyndaCourseIE(LyndaBaseIE):
course_path = mobj.group('coursepath')
course_id = mobj.group('courseid')
page = self._download_webpage(
course = self._download_json(
'http://www.lynda.com/ajax/player?courseId=%s&type=course' % course_id,
course_id, 'Downloading course JSON')
course_json = json.loads(page)
if 'Status' in course_json and course_json['Status'] == 'NotFound':
self._logout()
if course.get('Status') == 'NotFound':
raise ExtractorError(
'Course %s does not exist' % course_id, expected=True)
@ -219,12 +222,13 @@ class LyndaCourseIE(LyndaBaseIE):
# Might want to extract videos right here from video['Formats'] as it seems 'Formats' is not provided
# by single video API anymore
for chapter in course_json['Chapters']:
for video in chapter['Videos']:
if video['HasAccess'] is False:
for chapter in course['Chapters']:
for video in chapter.get('Videos', []):
if video.get('HasAccess') is False:
unaccessible_videos += 1
continue
videos.append(video['ID'])
if video.get('ID'):
videos.append(video['ID'])
if unaccessible_videos > 0:
self._downloader.report_warning(
@ -237,6 +241,6 @@ class LyndaCourseIE(LyndaBaseIE):
'Lynda')
for video_id in videos]
course_title = course_json['Title']
course_title = course.get('Title')
return self.playlist_result(entries, course_id, course_title)

187
youtube_dl/extractor/mdr.py
View File

@ -1,64 +1,169 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
determine_ext,
int_or_none,
parse_duration,
parse_iso8601,
xpath_text,
)
class MDRIE(InfoExtractor):
_VALID_URL = r'^(?P<domain>https?://(?:www\.)?mdr\.de)/(?:.*)/(?P<type>video|audio)(?P<video_id>[^/_]+)(?:_|\.html)'
IE_DESC = 'MDR.DE and KiKA'
_VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z]+(?P<id>\d+)(?:_.+?)?\.html'
# No tests, MDR regularily deletes its videos
_TEST = {
_TESTS = [{
# MDR regularily deletes its videos
'url': 'http://www.mdr.de/fakt/video189002.html',
'only_matching': True,
}
}, {
# audio
'url': 'http://www.mdr.de/kultur/audio1312272_zc-15948bad_zs-86171fdd.html',
'md5': '64c4ee50f0a791deb9479cd7bbe9d2fa',
'info_dict': {
'id': '1312272',
'ext': 'mp3',
'title': 'Feuilleton vom 30. Oktober 2015',
'duration': 250,
'uploader': 'MITTELDEUTSCHER RUNDFUNK',
},
}, {
'url': 'http://www.kika.de/baumhaus/videos/video19636.html',
'md5': '4930515e36b06c111213e80d1e4aad0e',
'info_dict': {
'id': '19636',
'ext': 'mp4',
'title': 'Baumhaus vom 30. Oktober 2015',
'duration': 134,
'uploader': 'KIKA',
},
}, {
'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/videos/video8182.html',
'md5': '5fe9c4dd7d71e3b238f04b8fdd588357',
'info_dict': {
'id': '8182',
'ext': 'mp4',
'title': 'Beutolomäus und der geheime Weihnachtswunsch',
'description': 'md5:b69d32d7b2c55cbe86945ab309d39bbd',
'timestamp': 1419047100,
'upload_date': '20141220',
'duration': 4628,
'uploader': 'KIKA',
},
}, {
'url': 'http://www.kika.de/baumhaus/sendungen/video19636_zc-fea7f8a0_zs-4bf89c60.html',
'only_matching': True,
}, {
'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/einzelsendung2534.html',
'only_matching': True,
}]
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('video_id')
domain = m.group('domain')
video_id = self._match_id(url)
# determine title and media streams from webpage
html = self._download_webpage(url, video_id)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h[12]>(.*?)</h[12]>', html, 'title')
xmlurl = self._search_regex(
r'dataURL:\'(/(?:.+)/(?:video|audio)[0-9]+-avCustom.xml)', html, 'XML URL')
data_url = self._search_regex(
r'dataURL\s*:\s*(["\'])(?P<url>/.+/(?:video|audio)[0-9]+-avCustom\.xml)\1',
webpage, 'data url', group='url')
doc = self._download_xml(
compat_urlparse.urljoin(url, data_url), video_id)
title = xpath_text(doc, ['./title', './broadcast/broadcastName'], 'title', fatal=True)
doc = self._download_xml(domain + xmlurl, video_id)
formats = []
for a in doc.findall('./assets/asset'):
url_el = a.find('./progressiveDownloadUrl')
if url_el is None:
continue
abr = int(a.find('bitrateAudio').text) // 1000
media_type = a.find('mediaType').text
format = {
'abr': abr,
'filesize': int(a.find('fileSize').text),
'url': url_el.text,
}
processed_urls = []
for asset in doc.findall('./assets/asset'):
for source in (
'progressiveDownload',
'dynamicHttpStreamingRedirector',
'adaptiveHttpStreamingRedirector'):
url_el = asset.find('./%sUrl' % source)
if url_el is None:
continue
video_url = url_el.text
if video_url in processed_urls:
continue
processed_urls.append(video_url)
vbr = int_or_none(xpath_text(asset, './bitrateVideo', 'vbr'), 1000)
abr = int_or_none(xpath_text(asset, './bitrateAudio', 'abr'), 1000)
ext = determine_ext(url_el.text)
if ext == 'm3u8':
url_formats = self._extract_m3u8_formats(
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
preference=0, m3u8_id='HLS', fatal=False)
elif ext == 'f4m':
url_formats = self._extract_f4m_formats(
video_url + '?hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id,
preference=0, f4m_id='HDS', fatal=False)
else:
media_type = xpath_text(asset, './mediaType', 'media type', default='MP4')
vbr = int_or_none(xpath_text(asset, './bitrateVideo', 'vbr'), 1000)
abr = int_or_none(xpath_text(asset, './bitrateAudio', 'abr'), 1000)
filesize = int_or_none(xpath_text(asset, './fileSize', 'file size'))
f = {
'url': video_url,
'format_id': '%s-%d' % (media_type, vbr or abr),
'filesize': filesize,
'abr': abr,
'preference': 1,
}
if vbr:
width = int_or_none(xpath_text(asset, './frameWidth', 'width'))
height = int_or_none(xpath_text(asset, './frameHeight', 'height'))
f.update({
'vbr': vbr,
'width': width,
'height': height,
})
url_formats = [f]
if not url_formats:
continue
if not vbr:
for f in url_formats:
abr = f.get('tbr') or abr
if 'tbr' in f:
del f['tbr']
f.update({
'abr': abr,
'vcodec': 'none',
})
formats.extend(url_formats)
vbr_el = a.find('bitrateVideo')
if vbr_el is None:
format.update({
'vcodec': 'none',
'format_id': '%s-%d' % (media_type, abr),
})
else:
vbr = int(vbr_el.text) // 1000
format.update({
'vbr': vbr,
'width': int(a.find('frameWidth').text),
'height': int(a.find('frameHeight').text),
'format_id': '%s-%d' % (media_type, vbr),
})
formats.append(format)
self._sort_formats(formats)
description = xpath_text(doc, './broadcast/broadcastDescription', 'description')
timestamp = parse_iso8601(
xpath_text(
doc, [
'./broadcast/broadcastDate',
'./broadcast/broadcastStartDate',
'./broadcast/broadcastEndDate'],
'timestamp', default=None))
duration = parse_duration(xpath_text(doc, './duration', 'duration'))
uploader = xpath_text(doc, './rights', 'uploader')
return {
'id': video_id,
'title': title,
'description': description,
'timestamp': timestamp,
'duration': duration,
'uploader': uploader,
'formats': formats,
}

13
youtube_dl/extractor/miomio.py
View File

@ -4,6 +4,7 @@ from __future__ import unicode_literals
import random
from .common import InfoExtractor
from ..compat import compat_urllib_request
from ..utils import (
xpath_text,
int_or_none,
@ -51,6 +52,8 @@ class MioMioIE(InfoExtractor):
mioplayer_path = self._search_regex(
r'src="(/mioplayer/[^"]+)"', webpage, 'ref_path')
http_headers = {'Referer': 'http://www.miomio.tv%s' % mioplayer_path}
xml_config = self._search_regex(
r'flashvars="type=(?:sina|video)&amp;(.+?)&amp;',
webpage, 'xml config')
@ -60,14 +63,12 @@ class MioMioIE(InfoExtractor):
'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/xml.php?id=%s&r=%s' % (id, random.randint(100, 999)),
video_id)
# the following xml contains the actual configuration information on the video file(s)
vid_config = self._download_xml(
vid_config_request = compat_urllib_request.Request(
'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/sina.php?{0}'.format(xml_config),
video_id)
headers=http_headers)
http_headers = {
'Referer': 'http://www.miomio.tv%s' % mioplayer_path,
}
# the following xml contains the actual configuration information on the video file(s)
vid_config = self._download_xml(vid_config_request, video_id)
if not int_or_none(xpath_text(vid_config, 'timelength')):
raise ExtractorError('Unable to load videos!', expected=True)

2
youtube_dl/extractor/mit.py
View File

@ -86,7 +86,7 @@ class MITIE(TechTVMITIE):
webpage = self._download_webpage(url, page_title)
embed_url = self._search_regex(
r'<iframe .*?src="(.+?)"', webpage, 'embed url')
return self.url_result(embed_url, ie='TechTVMIT')
return self.url_result(embed_url)
class OCWMITIE(InfoExtractor):

10
youtube_dl/extractor/mitele.py
View File

@ -1,7 +1,10 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urllib_parse
from ..compat import (
compat_urllib_parse,
compat_urlparse,
)
from ..utils import (
encode_dict,
get_element_by_attribute,
@ -15,7 +18,7 @@ class MiTeleIE(InfoExtractor):
_TESTS = [{
'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
'md5': 'ace7635b2a0b286aaa37d3ff192d2a8a',
'md5': '0ff1a13aebb35d9bc14081ff633dd324',
'info_dict': {
'id': '0NF1jJnxS1Wu3pHrmvFyw2',
'display_id': 'programa-144',
@ -34,6 +37,7 @@ class MiTeleIE(InfoExtractor):
config_url = self._search_regex(
r'data-config\s*=\s*"([^"]+)"', webpage, 'data config url')
config_url = compat_urlparse.urljoin(url, config_url)
config = self._download_json(
config_url, display_id, 'Downloading config JSON')
@ -56,7 +60,7 @@ class MiTeleIE(InfoExtractor):
'sta': '0',
}
media = self._download_json(
'%s/?%s' % (gat, compat_urllib_parse.urlencode(encode_dict(token_data)).encode('utf-8')),
'%s/?%s' % (gat, compat_urllib_parse.urlencode(encode_dict(token_data))),
display_id, 'Downloading %s JSON' % location['loc'])
file_ = media.get('file')
if not file_:

47
youtube_dl/extractor/moniker.py
View File

@ -17,7 +17,7 @@ from ..utils import (
class MonikerIE(InfoExtractor):
IE_DESC = 'allmyvideos.net and vidspot.net'
_VALID_URL = r'https?://(?:www\.)?(?:allmyvideos|vidspot)\.net/(?P<id>[a-zA-Z0-9_-]+)'
_VALID_URL = r'https?://(?:www\.)?(?:allmyvideos|vidspot)\.net/(?:(?:2|v)/v-)?(?P<id>[a-zA-Z0-9_-]+)'
_TESTS = [{
'url': 'http://allmyvideos.net/jih3nce3x6wn',
@ -46,6 +46,18 @@ class MonikerIE(InfoExtractor):
}, {
'url': 'https://www.vidspot.net/l2ngsmhs8ci5',
'only_matching': True,
}, {
'url': 'http://vidspot.net/2/v-ywDf99',
'md5': '5f8254ce12df30479428b0152fb8e7ba',
'info_dict': {
'id': 'ywDf99',
'ext': 'mp4',
'title': 'IL FAIT LE MALIN EN PORSHE CAYENNE ( mais pas pour longtemps)',
'description': 'IL FAIT LE MALIN EN PORSHE CAYENNE.',
},
}, {
'url': 'http://allmyvideos.net/v/v-HXZm5t',
'only_matching': True,
}]
def _real_extract(self, url):
@ -64,18 +76,30 @@ class MonikerIE(InfoExtractor):
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, error), expected=True)
fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage)
data = dict(fields)
builtin_url = self._search_regex(
r'<iframe[^>]+src=(["\'])(?P<url>.+?/builtin-.+?)\1',
orig_webpage, 'builtin URL', default=None, group='url')
post = compat_urllib_parse.urlencode(data)
headers = {
b'Content-Type': b'application/x-www-form-urlencoded',
}
req = compat_urllib_request.Request(url, post, headers)
webpage = self._download_webpage(
req, video_id, note='Downloading video page ...')
if builtin_url:
req = compat_urllib_request.Request(builtin_url)
req.add_header('Referer', url)
webpage = self._download_webpage(req, video_id, 'Downloading builtin page')
title = self._og_search_title(orig_webpage).strip()
description = self._og_search_description(orig_webpage).strip()
else:
fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage)
data = dict(fields)
title = os.path.splitext(data['fname'])[0]
post = compat_urllib_parse.urlencode(data)
headers = {
b'Content-Type': b'application/x-www-form-urlencoded',
}
req = compat_urllib_request.Request(url, post, headers)
webpage = self._download_webpage(
req, video_id, note='Downloading video page ...')
title = os.path.splitext(data['fname'])[0]
description = None
# Could be several links with different quality
links = re.findall(r'"file" : "?(.+?)",', webpage)
@ -89,5 +113,6 @@ class MonikerIE(InfoExtractor):
return {
'id': video_id,
'title': title,
'description': description,
'formats': formats,
}

78
youtube_dl/extractor/movieclips.py
View File

@ -1,80 +1,42 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_str,
)
from ..utils import (
ExtractorError,
clean_html,
compat_urllib_request,
)
class MovieClipsIE(InfoExtractor):
_VALID_URL = r'https?://movieclips\.com/(?P<id>[\da-zA-Z]+)(?:-(?P<display_id>[\da-z-]+))?'
_VALID_URL = r'https?://(?:www.)?movieclips\.com/videos/(?P<id>[^/?#]+)'
_TEST = {
'url': 'http://movieclips.com/Wy7ZU-my-week-with-marilyn-movie-do-you-love-me/',
'url': 'http://www.movieclips.com/videos/warcraft-trailer-1-561180739597?autoPlay=true&playlistId=5',
'info_dict': {
'id': 'Wy7ZU',
'display_id': 'my-week-with-marilyn-movie-do-you-love-me',
'id': 'pKIGmG83AqD9',
'display_id': 'warcraft-trailer-1-561180739597',
'ext': 'mp4',
'title': 'My Week with Marilyn - Do You Love Me?',
'description': 'md5:e86795bd332fe3cff461e7c8dc542acb',
'title': 'Warcraft Trailer 1',
'description': 'Watch Trailer 1 from Warcraft (2016). Legendary’s WARCRAFT is a 3D epic adventure of world-colliding conflict based.',
'thumbnail': 're:^https?://.*\.jpg$',
},
'params': {
# rtmp download
'skip_download': True,
}
'add_ie': ['ThePlatform'],
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id')
show_id = display_id or video_id
display_id = self._match_id(url)
config = self._download_xml(
'http://config.movieclips.com/player/config/%s' % video_id,
show_id, 'Downloading player config')
if config.find('./country-region').text == 'false':
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, config.find('./region_alert').text), expected=True)
properties = config.find('./video/properties')
smil_file = properties.attrib['smil_file']
smil = self._download_xml(smil_file, show_id, 'Downloading SMIL')
base_url = smil.find('./head/meta').attrib['base']
formats = []
for video in smil.findall('./body/switch/video'):
vbr = int(video.attrib['system-bitrate']) / 1000
src = video.attrib['src']
formats.append({
'url': base_url,
'play_path': src,
'ext': src.split(':')[0],
'vbr': vbr,
'format_id': '%dk' % vbr,
})
self._sort_formats(formats)
title = '%s - %s' % (properties.attrib['clip_movie_title'], properties.attrib['clip_title'])
description = clean_html(compat_str(properties.attrib['clip_description']))
thumbnail = properties.attrib['image']
categories = properties.attrib['clip_categories'].split(',')
req = compat_urllib_request.Request(url)
# it doesn't work if it thinks the browser it's too old
req.add_header('User-Agent', 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/43.0 (Chrome)')
webpage = self._download_webpage(req, display_id)
theplatform_link = self._html_search_regex(r'src="(http://player.theplatform.com/p/.*?)"', webpage, 'theplatform link')
title = self._html_search_regex(r'<title[^>]*>([^>]+)-\s*\d+\s*|\s*Movieclips.com</title>', webpage, 'title')
description = self._html_search_meta('description', webpage)
return {
'id': video_id,
'display_id': display_id,
'_type': 'url_transparent',
'url': theplatform_link,
'title': title,
'display_id': display_id,
'description': description,
'thumbnail': thumbnail,
'categories': categories,
'formats': formats,
}

17
youtube_dl/extractor/ndr.py
View File

@ -14,7 +14,8 @@ from ..utils import (
class NDRBaseIE(InfoExtractor):
def _real_extract(self, url):
display_id = self._match_id(url)
mobj = re.match(self._VALID_URL, url)
display_id = next(group for group in mobj.groups() if group)
webpage = self._download_webpage(url, display_id)
return self._extract_embed(webpage, display_id)
@ -22,7 +23,7 @@ class NDRBaseIE(InfoExtractor):
class NDRIE(NDRBaseIE):
IE_NAME = 'ndr'
IE_DESC = 'NDR.de - Norddeutscher Rundfunk'
_VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)+(?P<id>[^/?#]+),[\da-z]+\.html'
_VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)*(?P<id>[^/?#]+),[\da-z]+\.html'
_TESTS = [{
# httpVideo, same content id
'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html',
@ -77,6 +78,9 @@ class NDRIE(NDRBaseIE):
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.ndr.de/Fettes-Brot-Ferris-MC-und-Thees-Uhlmann-live-on-stage,festivalsommer116.html',
'only_matching': True,
}]
def _extract_embed(self, webpage, display_id):
@ -101,7 +105,7 @@ class NDRIE(NDRBaseIE):
class NJoyIE(NDRBaseIE):
IE_NAME = 'njoy'
IE_DESC = 'N-JOY'
_VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)+(?P<id>[^/?#]+),[\da-z]+\.html'
_VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)*(?:(?P<display_id>[^/?#]+),)?(?P<id>[\da-z]+)\.html'
_TESTS = [{
# httpVideo, same content id
'url': 'http://www.n-joy.de/entertainment/comedy/comedy_contest/Benaissa-beim-NDR-Comedy-Contest,comedycontest2480.html',
@ -136,6 +140,9 @@ class NJoyIE(NDRBaseIE):
'params': {
'skip_download': True,
},
}, {
'url': 'http://www.n-joy.de/radio/webradio/morningshow209.html',
'only_matching': True,
}]
def _extract_embed(self, webpage, display_id):
@ -231,7 +238,7 @@ class NDREmbedBaseIE(InfoExtractor):
class NDREmbedIE(NDREmbedBaseIE):
IE_NAME = 'ndr:embed'
_VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)+(?P<id>[\da-z]+)-(?:player|externalPlayer)\.html'
_VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)\.html'
_TESTS = [{
'url': 'http://www.ndr.de/fernsehen/sendungen/ndr_aktuell/ndraktuell28488-player.html',
'md5': '8b9306142fe65bbdefb5ce24edb6b0a9',
@ -325,7 +332,7 @@ class NDREmbedIE(NDREmbedBaseIE):
class NJoyEmbedIE(NDREmbedBaseIE):
IE_NAME = 'njoy:embed'
_VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)+(?P<id>[\da-z]+)-(?:player|externalPlayer)_[^/]+\.html'
_VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)_[^/]+\.html'
_TESTS = [{
# httpVideo
'url': 'http://www.n-joy.de/events/reeperbahnfestival/doku948-player_image-bc168e87-5263-4d6d-bd27-bb643005a6de_theme-n-joy.html',

5
youtube_dl/extractor/odnoklassniki.py
View File

@ -13,7 +13,7 @@ from ..utils import (
class OdnoklassnikiIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:odnoklassniki|ok)\.ru/(?:video|web-api/video/moviePlayer)/(?P<id>[\d-]+)'
_VALID_URL = r'https?://(?:www\.)?(?:odnoklassniki|ok)\.ru/(?:video(?:embed)?|web-api/video/moviePlayer)/(?P<id>[\d-]+)'
_TESTS = [{
# metadata in JSON
'url': 'http://ok.ru/video/20079905452',
@ -66,6 +66,9 @@ class OdnoklassnikiIE(InfoExtractor):
}, {
'url': 'http://www.ok.ru/video/20648036891',
'only_matching': True,
}, {
'url': 'http://www.ok.ru/videoembed/20648036891',
'only_matching': True,
}]
def _real_extract(self, url):

44
youtube_dl/extractor/pbs.py
View File

@ -8,6 +8,7 @@ from ..utils import (
ExtractorError,
determine_ext,
int_or_none,
strip_jsonp,
unified_strdate,
US_RATINGS,
)
@ -153,6 +154,22 @@ class PBSIE(InfoExtractor):
'params': {
'skip_download': True, # requires ffmpeg
},
},
{
# Frontline video embedded via flp2012.js
'url': 'http://www.pbs.org/wgbh/pages/frontline/the-atomic-artists',
'info_dict': {
'id': '2070868960',
'display_id': 'the-atomic-artists',
'ext': 'mp4',
'title': 'FRONTLINE - The Atomic Artists',
'description': 'md5:f5bfbefadf421e8bb8647602011caf8e',
'duration': 723,
'thumbnail': 're:^https?://.*\.jpg$',
},
'params': {
'skip_download': True, # requires ffmpeg
},
}
]
_ERRORS = {
@ -191,9 +208,30 @@ class PBSIE(InfoExtractor):
if media_id:
return media_id, presumptive_id, upload_date
url = self._search_regex(
r'(?s)<iframe[^>]+?(?:[a-z-]+?=["\'].*?["\'][^>]+?)*?\bsrc=["\']([^\'"]+partnerplayer[^\'"]+)["\']',
webpage, 'player URL')
# Fronline video embedded via flp
video_id = self._search_regex(
r'videoid\s*:\s*"([\d+a-z]{7,})"', webpage, 'videoid', default=None)
if video_id:
# pkg_id calculation is reverse engineered from
# http://www.pbs.org/wgbh/pages/frontline/js/flp2012.js
prg_id = self._search_regex(
r'videoid\s*:\s*"([\d+a-z]{7,})"', webpage, 'videoid')[7:]
if 'q' in prg_id:
prg_id = prg_id.split('q')[1]
prg_id = int(prg_id, 16)
getdir = self._download_json(
'http://www.pbs.org/wgbh/pages/frontline/.json/getdir/getdir%d.json' % prg_id,
presumptive_id, 'Downloading getdir JSON',
transform_source=strip_jsonp)
return getdir['mid'], presumptive_id, upload_date
for iframe in re.findall(r'(?s)<iframe(.+?)></iframe>', webpage):
url = self._search_regex(
r'src=(["\'])(?P<url>.+?partnerplayer.+?)\1', iframe,
'player URL', default=None, group='url')
if url:
break
mobj = re.match(self._VALID_URL, url)
player_id = mobj.group('player_id')

13
youtube_dl/extractor/periscope.py
View File

@ -12,7 +12,8 @@ from ..utils import parse_iso8601
class PeriscopeIE(InfoExtractor):
IE_DESC = 'Periscope'
_VALID_URL = r'https?://(?:www\.)?periscope\.tv/w/(?P<id>[^/?#]+)'
_TEST = {
# Alive example URLs can be found here http://onperiscope.com/
_TESTS = [{
'url': 'https://www.periscope.tv/w/aJUQnjY3MjA3ODF8NTYxMDIyMDl2zCg2pECBgwTqRpQuQD352EMPTKQjT4uqlM3cgWFA-g==',
'md5': '65b57957972e503fcbbaeed8f4fa04ca',
'info_dict': {
@ -25,11 +26,15 @@ class PeriscopeIE(InfoExtractor):
'uploader_id': '1465763',
},
'skip': 'Expires in 24 hours',
}
}, {
'url': 'https://www.periscope.tv/w/1ZkKzPbMVggJv',
'only_matching': True,
}]
def _call_api(self, method, token):
def _call_api(self, method, value):
attribute = 'token' if len(value) > 13 else 'broadcast_id'
return self._download_json(
'https://api.periscope.tv/api/v2/%s?token=%s' % (method, token), token)
'https://api.periscope.tv/api/v2/%s?%s=%s' % (method, attribute, value), value)
def _real_extract(self, url):
token = self._match_id(url)

2
youtube_dl/extractor/prosiebensat1.py
View File

@ -20,7 +20,7 @@ from ..utils import (
class ProSiebenSat1IE(InfoExtractor):
IE_NAME = 'prosiebensat1'
IE_DESC = 'ProSiebenSat.1 Digital'
_VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|the-voice-of-germany)\.(?:de|at)|ran\.de|fem\.com)/(?P<id>.+)'
_VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|the-voice-of-germany)\.(?:de|at|ch)|ran\.de|fem\.com)/(?P<id>.+)'
_TESTS = [
{

13
youtube_dl/extractor/rtbf.py
View File

@ -9,8 +9,8 @@ from ..utils import (
class RTBFIE(InfoExtractor):
_VALID_URL = r'https?://www.rtbf.be/video/[^\?]+\?id=(?P<id>\d+)'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?rtbf\.be/(?:video/[^?]+\?.*\bid=|ouftivi/(?:[^/]+/)*[^?]+\?.*\bvideoId=)(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.rtbf.be/video/detail_les-diables-au-coeur-episode-2?id=1921274',
'md5': '799f334ddf2c0a582ba80c44655be570',
'info_dict': {
@ -19,7 +19,14 @@ class RTBFIE(InfoExtractor):
'title': 'Les Diables au coeur (épisode 2)',
'duration': 3099,
}
}
}, {
# geo restricted
'url': 'http://www.rtbf.be/ouftivi/heros/detail_scooby-doo-mysteres-associes?id=1097&videoId=2057442',
'only_matching': True,
}, {
'url': 'http://www.rtbf.be/ouftivi/niouzz?videoId=2055858',
'only_matching': True,
}]
_QUALITIES = [
('mobile', 'mobile'),

12
youtube_dl/extractor/rte.py
View File

@ -9,16 +9,16 @@ from ..utils import (
class RteIE(InfoExtractor):
_VALID_URL = r'http?://(?:www\.)?rte\.ie/player/[^/]{2,3}/show/(?P<id>[0-9]+)/'
_VALID_URL = r'https?://(?:www\.)?rte\.ie/player/[^/]{2,3}/show/[^/]+/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.rte.ie/player/de/show/10363114/',
'url': 'http://www.rte.ie/player/ie/show/iwitness-862/10478715/',
'info_dict': {
'id': '10363114',
'id': '10478715',
'ext': 'mp4',
'title': 'One News',
'title': 'Watch iWitness online',
'thumbnail': 're:^https?://.*\.jpg$',
'description': 'The One O\'Clock News followed by Weather.',
'duration': 436.844,
'description': 'iWitness : The spirit of Ireland, one voice and one minute at a time.',
'duration': 60.046,
},
'params': {
'skip_download': 'f4m fails with --test atm'

4
youtube_dl/extractor/senateisvp.py
View File

@ -121,9 +121,9 @@ class SenateISVPIE(InfoExtractor):
'url': compat_urlparse.urljoin(domain, filename) + '?v=3.1.0&fp=&r=&g=',
}]
else:
hdcore_sign = '?hdcore=3.1.0'
hdcore_sign = 'hdcore=3.1.0'
url_params = (domain, video_id, stream_num)
f4m_url = '%s/z/%s_1@%s/manifest.f4m' % url_params + hdcore_sign
f4m_url = '%s/z/%s_1@%s/manifest.f4m?' % url_params + hdcore_sign
m3u8_url = '%s/i/%s_1@%s/master.m3u8' % url_params
for entry in self._extract_f4m_formats(f4m_url, video_id, f4m_id='f4m'):
# URLs without the extra param induce an 404 error

18
youtube_dl/extractor/spiegeltv.py
View File

@ -77,17 +77,21 @@ class SpiegeltvIE(InfoExtractor):
'rtmp_live': True,
})
elif determine_ext(endpoint) == 'm3u8':
m3u8_formats = self._extract_m3u8_formats(
endpoint.replace('[video]', play_path),
video_id, 'm4v',
preference=1, # Prefer hls since it allows to workaround georestriction
m3u8_id='hls', fatal=False)
if m3u8_formats is not False:
formats.extend(m3u8_formats)
formats.append({
'url': endpoint.replace('[video]', play_path),
'ext': 'm4v',
'format_id': 'hls', # Prefer hls since it allows to workaround georestriction
'protocol': 'm3u8',
'preference': 1,
'http_headers': {
'Accept-Encoding': 'deflate', # gzip causes trouble on the server side
},
})
else:
formats.append({
'url': endpoint,
})
self._check_formats(formats, video_id)
thumbnails = []
for image in media_json['images']:

81
youtube_dl/extractor/stitcher.py Normal file
View File

@ -0,0 +1,81 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
int_or_none,
js_to_json,
unescapeHTML,
)
class StitcherIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?stitcher\.com/podcast/(?:[^/]+/)+e/(?:(?P<display_id>[^/#?&]+?)-)?(?P<id>\d+)(?:[/#?&]|$)'
_TESTS = [{
'url': 'http://www.stitcher.com/podcast/the-talking-machines/e/40789481?autoplay=true',
'md5': '391dd4e021e6edeb7b8e68fbf2e9e940',
'info_dict': {
'id': '40789481',
'ext': 'mp3',
'title': 'Machine Learning Mastery and Cancer Clusters',
'description': 'md5:55163197a44e915a14a1ac3a1de0f2d3',
'duration': 1604,
'thumbnail': 're:^https?://.*\.jpg',
},
}, {
'url': 'http://www.stitcher.com/podcast/panoply/vulture-tv/e/the-rare-hourlong-comedy-plus-40846275?autoplay=true',
'info_dict': {
'id': '40846275',
'display_id': 'the-rare-hourlong-comedy-plus',
'ext': 'mp3',
'title': "The CW's 'Crazy Ex-Girlfriend'",
'description': 'md5:04f1e2f98eb3f5cbb094cea0f9e19b17',
'duration': 2235,
'thumbnail': 're:^https?://.*\.jpg',
},
'params': {
'skip_download': True,
},
}, {
# escaped title
'url': 'http://www.stitcher.com/podcast/marketplace-on-stitcher/e/40910226?autoplay=true',
'only_matching': True,
}, {
'url': 'http://www.stitcher.com/podcast/panoply/getting-in/e/episode-2a-how-many-extracurriculars-should-i-have-40876278?autoplay=true',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
audio_id = mobj.group('id')
display_id = mobj.group('display_id') or audio_id
webpage = self._download_webpage(url, display_id)
episode = self._parse_json(
js_to_json(self._search_regex(
r'(?s)var\s+stitcher\s*=\s*({.+?});\n', webpage, 'episode config')),
display_id)['config']['episode']
title = unescapeHTML(episode['title'])
formats = [{
'url': episode[episode_key],
'ext': determine_ext(episode[episode_key]) or 'mp3',
'vcodec': 'none',
} for episode_key in ('episodeURL',) if episode.get(episode_key)]
description = self._search_regex(
r'Episode Info:\s*</span>([^<]+)<', webpage, 'description', fatal=False)
duration = int_or_none(episode.get('duration'))
thumbnail = episode.get('episodeImage')
return {
'id': audio_id,
'display_id': display_id,
'title': title,
'description': description,
'duration': duration,
'thumbnail': thumbnail,
'formats': formats,
}

4
youtube_dl/extractor/tutv.py
View File

@ -10,10 +10,10 @@ class TutvIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tu\.tv/videos/(?P<id>[^/?]+)'
_TEST = {
'url': 'http://tu.tv/videos/robots-futbolistas',
'md5': '627c7c124ac2a9b5ab6addb94e0e65f7',
'md5': '0cd9e28ad270488911b0d2a72323395d',
'info_dict': {
'id': '2973058',
'ext': 'flv',
'ext': 'mp4',
'title': 'Robots futbolistas',
},
}

34
youtube_dl/extractor/twitch.py
View File

@ -15,6 +15,7 @@ from ..compat import (
compat_urlparse,
)
from ..utils import (
encode_dict,
ExtractorError,
int_or_none,
parse_duration,
@ -27,8 +28,7 @@ class TwitchBaseIE(InfoExtractor):
_API_BASE = 'https://api.twitch.tv'
_USHER_BASE = 'http://usher.twitch.tv'
_LOGIN_URL = 'https://secure.twitch.tv/login'
_LOGIN_POST_URL = 'https://passport.twitch.tv/authentications/new'
_LOGIN_URL = 'http://www.twitch.tv/login'
_NETRC_MACHINE = 'twitch'
def _handle_error(self, response):
@ -61,26 +61,28 @@ class TwitchBaseIE(InfoExtractor):
if username is None:
return
login_page = self._download_webpage(
login_page, handle = self._download_webpage_handle(
self._LOGIN_URL, None, 'Downloading login page')
login_form = self._hidden_inputs(login_page)
login_form.update({
'login': username.encode('utf-8'),
'password': password.encode('utf-8'),
'username': username,
'password': password,
})
redirect_url = handle.geturl()
post_url = self._search_regex(
r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
'post url', default=self._LOGIN_POST_URL, group='url')
'post url', default=redirect_url, group='url')
if not post_url.startswith('http'):
post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
post_url = compat_urlparse.urljoin(redirect_url, post_url)
request = compat_urllib_request.Request(
post_url, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
request.add_header('Referer', self._LOGIN_URL)
post_url, compat_urllib_parse.urlencode(encode_dict(login_form)).encode('utf-8'))
request.add_header('Referer', redirect_url)
response = self._download_webpage(
request, None, 'Logging in as %s' % username)
@ -238,14 +240,24 @@ class TwitchVodIE(TwitchItemBaseIE):
def _real_extract(self, url):
item_id = self._match_id(url)
info = self._download_info(self._ITEM_SHORTCUT, item_id)
access_token = self._download_json(
'%s/api/vods/%s/access_token' % (self._API_BASE, item_id), item_id,
'Downloading %s access token' % self._ITEM_TYPE)
formats = self._extract_m3u8_formats(
'%s/vod/%s?nauth=%s&nauthsig=%s&allow_source=true'
% (self._USHER_BASE, item_id, access_token['token'], access_token['sig']),
'%s/vod/%s?%s' % (
self._USHER_BASE, item_id,
compat_urllib_parse.urlencode({
'allow_source': 'true',
'allow_spectre': 'true',
'player': 'twitchweb',
'nauth': access_token['token'],
'nauthsig': access_token['sig'],
})),
item_id, 'mp4')
self._prefer_source(formats)
info['formats'] = formats

122
youtube_dl/extractor/twitter.py
View File

@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
import re
@ -6,23 +7,51 @@ from .common import InfoExtractor
from ..compat import compat_urllib_request
from ..utils import (
float_or_none,
unescapeHTML,
xpath_text,
remove_end,
)
class TwitterCardIE(InfoExtractor):
IE_NAME = 'twitter:card'
_VALID_URL = r'https?://(?:www\.)?twitter\.com/i/cards/tfw/v1/(?P<id>\d+)'
_TEST = {
'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889',
'md5': 'a74f50b310c83170319ba16de6955192',
'info_dict': {
'id': '560070183650213889',
'ext': 'mp4',
'title': 'TwitterCard',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 30.033,
_TESTS = [
{
'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889',
'md5': '7d2f6b4d2eb841a7ccc893d479bfceb4',
'info_dict': {
'id': '560070183650213889',
'ext': 'mp4',
'title': 'TwitterCard',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 30.033,
}
},
}
{
'url': 'https://twitter.com/i/cards/tfw/v1/623160978427936768',
'md5': '7ee2a553b63d1bccba97fbed97d9e1c8',
'info_dict': {
'id': '623160978427936768',
'ext': 'mp4',
'title': 'TwitterCard',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 80.155,
},
},
{
'url': 'https://twitter.com/i/cards/tfw/v1/654001591733886977',
'md5': 'b6f35e8b08a0bec6c8af77a2f4b3a814',
'info_dict': {
'id': 'dq4Oj5quskI',
'ext': 'mp4',
'title': 'Ubuntu 11.10 Overview',
'description': 'Take a quick peek at what\'s new and improved in Ubuntu 11.10.\n\nOnce installed take a look at 10 Things to Do After Installing: http://www.omgubuntu.co.uk/2011/10/10-things-to-do-after-installing-ubuntu-11-10/',
'upload_date': '20111013',
'uploader': 'OMG! Ubuntu!',
'uploader_id': 'omgubuntu',
},
}
]
def _real_extract(self, url):
video_id = self._match_id(url)
@ -40,10 +69,24 @@ class TwitterCardIE(InfoExtractor):
request.add_header('User-Agent', user_agent)
webpage = self._download_webpage(request, video_id)
config = self._parse_json(
unescapeHTML(self._search_regex(
r'data-player-config="([^"]+)"', webpage, 'data player config')),
youtube_url = self._html_search_regex(
r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
webpage, 'youtube iframe', default=None)
if youtube_url:
return self.url_result(youtube_url, 'Youtube')
config = self._parse_json(self._html_search_regex(
r'data-player-config="([^"]+)"', webpage, 'data player config'),
video_id)
if 'playlist' not in config:
if 'vmapUrl' in config:
vmap_data = self._download_xml(config['vmapUrl'], video_id)
video_url = xpath_text(vmap_data, './/MediaFile').strip()
formats.append({
'url': video_url,
})
break # same video regardless of UA
continue
video_url = config['playlist'][0]['source']
@ -70,3 +113,54 @@ class TwitterCardIE(InfoExtractor):
'duration': duration,
'formats': formats,
}
class TwitterIE(InfoExtractor):
IE_NAME = 'twitter'
_VALID_URL = r'https?://(?:www\.|m\.|mobile\.)?twitter\.com/(?P<user_id>[^/]+)/status/(?P<id>\d+)'
_TEMPLATE_URL = 'https://twitter.com/%s/status/%s'
_TEST = {
'url': 'https://twitter.com/freethenipple/status/643211948184596480',
'md5': '31cd83a116fc41f99ae3d909d4caf6a0',
'info_dict': {
'id': '643211948184596480',
'ext': 'mp4',
'title': 'FREE THE NIPPLE - FTN supporters on Hollywood Blvd today!',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 12.922,
'description': 'FREE THE NIPPLE on Twitter: "FTN supporters on Hollywood Blvd today! http://t.co/c7jHH749xJ"',
'uploader': 'FREE THE NIPPLE',
'uploader_id': 'freethenipple',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
user_id = mobj.group('user_id')
twid = mobj.group('id')
webpage = self._download_webpage(self._TEMPLATE_URL % (user_id, twid), twid)
username = remove_end(self._og_search_title(webpage), ' on Twitter')
title = self._og_search_description(webpage).strip('').replace('\n', ' ')
# strip 'https -_t.co_BJYgOjSeGA' junk from filenames
mobj = re.match(r'“(.*)\s+(https?://[^ ]+)”', title)
title, short_url = mobj.groups()
card_id = self._search_regex(
r'["\']/i/cards/tfw/v1/(\d+)', webpage, 'twitter card url')
card_url = 'https://twitter.com/i/cards/tfw/v1/' + card_id
return {
'_type': 'url_transparent',
'ie_key': 'TwitterCard',
'uploader_id': user_id,
'uploader': username,
'url': card_url,
'webpage_url': url,
'description': '%s on Twitter: "%s %s"' % (username, title, short_url),
'title': username + ' - ' + title,
}

6
youtube_dl/extractor/vevo.py
View File

@ -1,10 +1,10 @@
from __future__ import unicode_literals
import re
import xml.etree.ElementTree
from .common import InfoExtractor
from ..compat import (
compat_etree_fromstring,
compat_urllib_request,
)
from ..utils import (
@ -97,7 +97,7 @@ class VevoIE(InfoExtractor):
if last_version['version'] == -1:
raise ExtractorError('Unable to extract last version of the video')
renditions = xml.etree.ElementTree.fromstring(last_version['data'])
renditions = compat_etree_fromstring(last_version['data'])
formats = []
# Already sorted from worst to best quality
for rend in renditions.findall('rendition'):
@ -114,7 +114,7 @@ class VevoIE(InfoExtractor):
def _formats_from_smil(self, smil_xml):
formats = []
smil_doc = xml.etree.ElementTree.fromstring(smil_xml.encode('utf-8'))
smil_doc = compat_etree_fromstring(smil_xml.encode('utf-8'))
els = smil_doc.findall('.//{http://www.w3.org/2001/SMIL20/Language}video')
for el in els:
src = el.attrib['src']

40
youtube_dl/extractor/videofyme.py
View File

@ -2,8 +2,8 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
find_xpath_attr,
int_or_none,
parse_iso8601,
)
@ -18,33 +18,35 @@ class VideofyMeIE(InfoExtractor):
'id': '1100701',
'ext': 'mp4',
'title': 'This is VideofyMe',
'description': None,
'description': '',
'upload_date': '20130326',
'timestamp': 1364288959,
'uploader': 'VideofyMe',
'uploader_id': 'thisisvideofyme',
'view_count': int,
'likes': int,
'comment_count': int,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
config = self._download_xml('http://sunshine.videofy.me/?videoId=%s' % video_id,
video_id)
video = config.find('video')
sources = video.find('sources')
url_node = next(node for node in [find_xpath_attr(sources, 'source', 'id', 'HQ %s' % key)
for key in ['on', 'av', 'off']] if node is not None)
video_url = url_node.find('url').text
view_count = int_or_none(self._search_regex(
r'([0-9]+)', video.find('views').text, 'view count', fatal=False))
config = self._download_json('http://vf-player-info-loader.herokuapp.com/%s.json' % video_id, video_id)['videoinfo']
video = config.get('video')
blog = config.get('blog', {})
return {
'id': video_id,
'title': video.find('title').text,
'url': video_url,
'thumbnail': video.find('thumb').text,
'description': video.find('description').text,
'uploader': config.find('blog/name').text,
'uploader_id': video.find('identifier').text,
'view_count': view_count,
'title': video['title'],
'url': video['sources']['source']['url'],
'thumbnail': video.get('thumb'),
'description': video.get('description'),
'timestamp': parse_iso8601(video.get('date')),
'uploader': blog.get('name'),
'uploader_id': blog.get('identifier'),
'view_count': int_or_none(self._search_regex(r'([0-9]+)', video.get('views'), 'view count', fatal=False)),
'likes': int_or_none(video.get('likes')),
'comment_count': int_or_none(video.get('nrOfComments')),
}

82
youtube_dl/extractor/videolecturesnet.py
View File

@ -1,82 +0,0 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_urlparse,
)
from ..utils import (
ExtractorError,
parse_duration,
)
class VideoLecturesNetIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?videolectures\.net/(?P<id>[^/#?]+)/*(?:[#?].*)?$'
IE_NAME = 'videolectures.net'
_TESTS = [{
'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/',
'info_dict': {
'id': 'promogram_igor_mekjavic_eng',
'ext': 'mp4',
'title': 'Automatics, robotics and biocybernetics',
'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
'upload_date': '20130627',
'duration': 565,
'thumbnail': 're:http://.*\.jpg',
},
}, {
# video with invalid direct format links (HTTP 403)
'url': 'http://videolectures.net/russir2010_filippova_nlp/',
'info_dict': {
'id': 'russir2010_filippova_nlp',
'ext': 'flv',
'title': 'NLP at Google',
'description': 'md5:fc7a6d9bf0302d7cc0e53f7ca23747b3',
'duration': 5352,
'thumbnail': 're:http://.*\.jpg',
},
'params': {
# rtmp download
'skip_download': True,
},
}, {
'url': 'http://videolectures.net/deeplearning2015_montreal/',
'info_dict': {
'id': 'deeplearning2015_montreal',
'title': 'Deep Learning Summer School, Montreal 2015',
'description': 'md5:90121a40cc6926df1bf04dcd8563ed3b',
},
'playlist_count': 30,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
smil_url = 'http://videolectures.net/%s/video/1/smil.xml' % video_id
try:
smil = self._download_smil(smil_url, video_id)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
# Probably a playlist
webpage = self._download_webpage(url, video_id)
entries = [
self.url_result(compat_urlparse.urljoin(url, video_url), 'VideoLecturesNet')
for _, video_url in re.findall(r'<a[^>]+href=(["\'])(.+?)\1[^>]+id=["\']lec=\d+', webpage)]
playlist_title = self._html_search_meta('title', webpage, 'title', fatal=True)
playlist_description = self._html_search_meta('description', webpage, 'description')
return self.playlist_result(entries, video_id, playlist_title, playlist_description)
info = self._parse_smil(smil, smil_url, video_id)
info['id'] = video_id
switch = smil.find('.//switch')
if switch is not None:
info['duration'] = parse_duration(switch.attrib.get('dur'))
return info

56
youtube_dl/extractor/vidme.py
View File

@ -14,7 +14,7 @@ class VidmeIE(InfoExtractor):
_VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]+)'
_TESTS = [{
'url': 'https://vid.me/QNB',
'md5': 'c62f1156138dc3323902188c5b5a8bd6',
'md5': 'f42d05e7149aeaec5c037b17e5d3dc82',
'info_dict': {
'id': 'QNB',
'ext': 'mp4',
@ -93,6 +93,39 @@ class VidmeIE(InfoExtractor):
'params': {
'skip_download': True,
},
}, {
# nsfw, user-disabled
'url': 'https://vid.me/dzGJ',
'only_matching': True,
}, {
# suspended
'url': 'https://vid.me/Ox3G',
'only_matching': True,
}, {
# deleted
'url': 'https://vid.me/KTPm',
'only_matching': True,
}, {
# no formats in the API response
'url': 'https://vid.me/e5g',
'info_dict': {
'id': 'e5g',
'ext': 'mp4',
'title': 'Video upload (e5g)',
'thumbnail': 're:^https?://.*\.jpg',
'timestamp': 1401480195,
'upload_date': '20140530',
'uploader': None,
'uploader_id': None,
'age_limit': 0,
'duration': 483,
'view_count': int,
'like_count': int,
'comment_count': int,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
@ -114,6 +147,17 @@ class VidmeIE(InfoExtractor):
video = response['video']
if video.get('state') == 'deleted':
raise ExtractorError(
'Vidme said: Sorry, this video has been deleted.',
expected=True)
if video.get('state') in ('user-disabled', 'suspended'):
raise ExtractorError(
'Vidme said: This video has been suspended either due to a copyright claim, '
'or for violating the terms of use.',
expected=True)
formats = [{
'format_id': f.get('type'),
'url': f['uri'],
@ -121,6 +165,14 @@ class VidmeIE(InfoExtractor):
'height': int_or_none(f.get('height')),
'preference': 0 if f.get('type', '').endswith('clip') else 1,
} for f in video.get('formats', []) if f.get('uri')]
if not formats and video.get('complete_url'):
formats.append({
'url': video.get('complete_url'),
'width': int_or_none(video.get('width')),
'height': int_or_none(video.get('height')),
})
self._sort_formats(formats)
title = video['title']
@ -137,7 +189,7 @@ class VidmeIE(InfoExtractor):
return {
'id': video_id,
'title': title,
'title': title or 'Video upload (%s)' % video_id,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,

10
youtube_dl/extractor/vidzi.py
View File

@ -20,8 +20,14 @@ class VidziIE(InfoExtractor):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_url = self._html_search_regex(
r'{\s*file\s*:\s*"([^"]+)"\s*}', webpage, 'video url')
video_host = self._html_search_regex(
r'id=\'vplayer\'><img src="http://(.*?)/i', webpage,
'video host')
video_hash = self._html_search_regex(
r'\|([a-z0-9]+)\|hls\|type', webpage, 'video_hash')
ext = self._html_search_regex(
r'\|tracks\|([a-z0-9]+)\|', webpage, 'video ext')
video_url = 'http://' + video_host + '/' + video_hash + '/v.' + ext
title = self._html_search_regex(
r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title')

7
youtube_dl/extractor/viewster.py
View File

@ -131,10 +131,11 @@ class ViewsterIE(InfoExtractor):
formats.extend(self._extract_f4m_formats(
video_url, video_id, f4m_id='hds'))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
m3u8_formats = self._extract_m3u8_formats(
video_url, video_id, 'mp4', m3u8_id='hls',
fatal=False # m3u8 sometimes fail
))
fatal=False) # m3u8 sometimes fail
if m3u8_formats:
formats.extend(m3u8_formats)
else:
format_id = media.get('Bitrate')
f = {

188
youtube_dl/extractor/viidea.py Normal file
View File

@ -0,0 +1,188 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_urlparse,
compat_str,
)
from ..utils import (
parse_duration,
js_to_json,
parse_iso8601,
)
class ViideaIE(InfoExtractor):
_VALID_URL = r'''(?x)http://(?:www\.)?(?:
videolectures\.net|
flexilearn\.viidea\.net|
presentations\.ocwconsortium\.org|
video\.travel-zoom\.si|
video\.pomp-forum\.si|
tv\.nil\.si|
video\.hekovnik.com|
video\.szko\.si|
kpk\.viidea\.com|
inside\.viidea\.net|
video\.kiberpipa\.org|
bvvideo\.si|
kongres\.viidea\.net|
edemokracija\.viidea\.com
)(?:/lecture)?/(?P<id>[^/]+)(?:/video/(?P<part>\d+))?/*(?:[#?].*)?$'''
_TESTS = [{
'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/',
'info_dict': {
'id': '20171',
'display_id': 'promogram_igor_mekjavic_eng',
'ext': 'mp4',
'title': 'Automatics, robotics and biocybernetics',
'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
'thumbnail': 're:http://.*\.jpg',
'timestamp': 1372349289,
'upload_date': '20130627',
'duration': 565,
},
}, {
# video with invalid direct format links (HTTP 403)
'url': 'http://videolectures.net/russir2010_filippova_nlp/',
'info_dict': {
'id': '14891',
'display_id': 'russir2010_filippova_nlp',
'ext': 'flv',
'title': 'NLP at Google',
'description': 'md5:fc7a6d9bf0302d7cc0e53f7ca23747b3',
'thumbnail': 're:http://.*\.jpg',
'timestamp': 1284375600,
'upload_date': '20100913',
'duration': 5352,
},
'params': {
# rtmp download
'skip_download': True,
},
}, {
# event playlist
'url': 'http://videolectures.net/deeplearning2015_montreal/',
'info_dict': {
'id': '23181',
'title': 'Deep Learning Summer School, Montreal 2015',
'description': 'md5:0533a85e4bd918df52a01f0e1ebe87b7',
'thumbnail': 're:http://.*\.jpg',
'timestamp': 1438560000,
},
'playlist_count': 30,
}, {
# multi part lecture
'url': 'http://videolectures.net/mlss09uk_bishop_ibi/',
'info_dict': {
'id': '9737',
'display_id': 'mlss09uk_bishop_ibi',
'title': 'Introduction To Bayesian Inference',
'thumbnail': 're:http://.*\.jpg',
'timestamp': 1251622800,
},
'playlist': [{
'info_dict': {
'id': '9737_part1',
'display_id': 'mlss09uk_bishop_ibi_part1',
'ext': 'wmv',
'title': 'Introduction To Bayesian Inference (Part 1)',
'thumbnail': 're:http://.*\.jpg',
'duration': 4622,
'timestamp': 1251622800,
'upload_date': '20090830',
},
}, {
'info_dict': {
'id': '9737_part2',
'display_id': 'mlss09uk_bishop_ibi_part2',
'ext': 'wmv',
'title': 'Introduction To Bayesian Inference (Part 2)',
'thumbnail': 're:http://.*\.jpg',
'duration': 5641,
'timestamp': 1251622800,
'upload_date': '20090830',
},
}],
'playlist_count': 2,
}]
def _real_extract(self, url):
lecture_slug, explicit_part_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, lecture_slug)
cfg = self._parse_json(self._search_regex(
[r'cfg\s*:\s*({.+?})\s*,\s*[\da-zA-Z_]+\s*:\s*\(?\s*function',
r'cfg\s*:\s*({[^}]+})'],
webpage, 'cfg'), lecture_slug, js_to_json)
lecture_id = compat_str(cfg['obj_id'])
base_url = self._proto_relative_url(cfg['livepipe'], 'http:')
lecture_data = self._download_json(
'%s/site/api/lecture/%s?format=json' % (base_url, lecture_id),
lecture_id)['lecture'][0]
lecture_info = {
'id': lecture_id,
'display_id': lecture_slug,
'title': lecture_data['title'],
'timestamp': parse_iso8601(lecture_data.get('time')),
'description': lecture_data.get('description_wiki'),
'thumbnail': lecture_data.get('thumb'),
}
playlist_entries = []
lecture_type = lecture_data.get('type')
parts = [compat_str(video) for video in cfg.get('videos', [])]
if parts:
multipart = len(parts) > 1
def extract_part(part_id):
smil_url = '%s/%s/video/%s/smil.xml' % (base_url, lecture_slug, part_id)
smil = self._download_smil(smil_url, lecture_id)
info = self._parse_smil(smil, smil_url, lecture_id)
info['id'] = lecture_id if not multipart else '%s_part%s' % (lecture_id, part_id)
info['display_id'] = lecture_slug if not multipart else '%s_part%s' % (lecture_slug, part_id)
if multipart:
info['title'] += ' (Part %s)' % part_id
switch = smil.find('.//switch')
if switch is not None:
info['duration'] = parse_duration(switch.attrib.get('dur'))
item_info = lecture_info.copy()
item_info.update(info)
return item_info
if explicit_part_id or not multipart:
result = extract_part(explicit_part_id or parts[0])
else:
result = {
'_type': 'multi_video',
'entries': [extract_part(part) for part in parts],
}
result.update(lecture_info)
# Immediately return explicitly requested part or non event item
if explicit_part_id or lecture_type != 'evt':
return result
playlist_entries.append(result)
# It's probably a playlist
if not parts or lecture_type == 'evt':
playlist_webpage = self._download_webpage(
'%s/site/ajax/drilldown/?id=%s' % (base_url, lecture_id), lecture_id)
entries = [
self.url_result(compat_urlparse.urljoin(url, video_url), 'Viidea')
for _, video_url in re.findall(
r'<a[^>]+href=(["\'])(.+?)\1[^>]+id=["\']lec=\d+', playlist_webpage)]
playlist_entries.extend(entries)
playlist = self.playlist_result(playlist_entries, lecture_id)
playlist.update(lecture_info)
return playlist

37
youtube_dl/extractor/vimeo.py
View File

@ -8,11 +8,11 @@ import itertools
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_urllib_parse,
compat_urllib_request,
compat_urlparse,
)
from ..utils import (
encode_dict,
ExtractorError,
InAdvancePagedList,
int_or_none,
@ -40,13 +40,13 @@ class VimeoBaseInfoExtractor(InfoExtractor):
self.report_login()
webpage = self._download_webpage(self._LOGIN_URL, None, False)
token, vuid = self._extract_xsrft_and_vuid(webpage)
data = urlencode_postdata({
data = urlencode_postdata(encode_dict({
'action': 'login',
'email': username,
'password': password,
'service': 'vimeo',
'token': token,
})
}))
login_request = compat_urllib_request.Request(self._LOGIN_URL, data)
login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
login_request.add_header('Cookie', 'vuid=%s' % vuid)
@ -133,7 +133,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'uploader_id': 'user18948128',
'uploader': 'Jaime Marquínez Ferrándiz',
'duration': 10,
'description': 'This is "youtube-dl password protected test video" by Jaime Marquínez Ferrándiz on Vimeo, the home for high quality videos and the people who love them.',
'description': 'This is "youtube-dl password protected test video" by Jaime Marquínez Ferrándiz on Vimeo, the home for high quality videos and the people\u2026',
},
'params': {
'videopassword': 'youtube-dl',
@ -181,6 +181,11 @@ class VimeoIE(VimeoBaseInfoExtractor):
'uploader_id': 'user28849593',
},
},
{
'url': 'https://vimeo.com/109815029',
'note': 'Video not completely processed, "failed" seed status',
'only_matching': True,
},
]
@staticmethod
@ -203,10 +208,10 @@ class VimeoIE(VimeoBaseInfoExtractor):
if password is None:
raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
token, vuid = self._extract_xsrft_and_vuid(webpage)
data = urlencode_postdata({
data = urlencode_postdata(encode_dict({
'password': password,
'token': token,
})
}))
if url.startswith('http://'):
# vimeo only supports https now, but the user can give an http url
url = url.replace('http://', 'https://')
@ -222,7 +227,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
password = self._downloader.params.get('videopassword', None)
if password is None:
raise ExtractorError('This video is protected by a password, use the --video-password option')
data = compat_urllib_parse.urlencode({'password': password})
data = urlencode_postdata(encode_dict({'password': password}))
pass_url = url + '/check-password'
password_request = compat_urllib_request.Request(pass_url, data)
password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
@ -273,20 +278,30 @@ class VimeoIE(VimeoBaseInfoExtractor):
self.report_extraction(video_id)
vimeo_config = self._search_regex(
r'vimeo\.config\s*=\s*({.+?});', webpage,
r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage,
'vimeo config', default=None)
if vimeo_config:
seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
if seed_status.get('state') == 'failed':
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, seed_status['title']),
'%s said: %s' % (self.IE_NAME, seed_status['title']),
expected=True)
# Extract the config JSON
try:
try:
config_url = self._html_search_regex(
r' data-config-url="(.+?)"', webpage, 'config URL')
r' data-config-url="(.+?)"', webpage,
'config URL', default=None)
if not config_url:
# Sometimes new react-based page is served instead of old one that require
# different config URL extraction approach (see
# https://github.com/rg3/youtube-dl/pull/7209)
vimeo_clip_page_config = self._search_regex(
r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
'vimeo clip page config')
config_url = self._parse_json(
vimeo_clip_page_config, video_id)['player']['config_url']
config_json = self._download_webpage(config_url, video_id)
config = json.loads(config_json)
except RegexNotFoundError:
@ -473,7 +488,7 @@ class VimeoChannelIE(VimeoBaseInfoExtractor):
token, vuid = self._extract_xsrft_and_vuid(webpage)
fields['token'] = token
fields['password'] = password
post = urlencode_postdata(fields)
post = urlencode_postdata(encode_dict(fields))
password_path = self._search_regex(
r'action="([^"]+)"', login_form, 'password URL')
password_url = compat_urlparse.urljoin(page_url, password_path)

70
youtube_dl/extractor/vine.py
View File

@ -1,10 +1,14 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import itertools
from .common import InfoExtractor
from ..utils import unified_strdate
from ..utils import (
int_or_none,
unified_strdate,
)
class VineIE(InfoExtractor):
@ -17,10 +21,12 @@ class VineIE(InfoExtractor):
'ext': 'mp4',
'title': 'Chicken.',
'alt_title': 'Vine by Jack Dorsey',
'description': 'Chicken.',
'upload_date': '20130519',
'uploader': 'Jack Dorsey',
'uploader_id': '76',
'like_count': int,
'comment_count': int,
'repost_count': int,
},
}, {
'url': 'https://vine.co/v/MYxVapFvz2z',
@ -29,11 +35,13 @@ class VineIE(InfoExtractor):
'id': 'MYxVapFvz2z',
'ext': 'mp4',
'title': 'Fuck Da Police #Mikebrown #justice #ferguson #prayforferguson #protesting #NMOS14',
'alt_title': 'Vine by Luna',
'description': 'Fuck Da Police #Mikebrown #justice #ferguson #prayforferguson #protesting #NMOS14',
'alt_title': 'Vine by Mars Ruiz',
'upload_date': '20140815',
'uploader': 'Luna',
'uploader': 'Mars Ruiz',
'uploader_id': '1102363502380728320',
'like_count': int,
'comment_count': int,
'repost_count': int,
},
}, {
'url': 'https://vine.co/v/bxVjBbZlPUH',
@ -43,14 +51,33 @@ class VineIE(InfoExtractor):
'ext': 'mp4',
'title': '#mw3 #ac130 #killcam #angelofdeath',
'alt_title': 'Vine by Z3k3',
'description': '#mw3 #ac130 #killcam #angelofdeath',
'upload_date': '20130430',
'uploader': 'Z3k3',
'uploader_id': '936470460173008896',
'like_count': int,
'comment_count': int,
'repost_count': int,
},
}, {
'url': 'https://vine.co/oembed/MYxVapFvz2z.json',
'only_matching': True,
}, {
'url': 'https://vine.co/v/e192BnZnZ9V',
'info_dict': {
'id': 'e192BnZnZ9V',
'ext': 'mp4',
'title': 'ยิ้ม~ เขิน~ อาย~ น่าร้ากอ้ะ >//< @n_whitewo @orlameena #lovesicktheseries #lovesickseason2',
'alt_title': 'Vine by Pimry_zaa',
'upload_date': '20150705',
'uploader': 'Pimry_zaa',
'uploader_id': '1135760698325307392',
'like_count': int,
'comment_count': int,
'repost_count': int,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
@ -58,32 +85,33 @@ class VineIE(InfoExtractor):
webpage = self._download_webpage('https://vine.co/v/' + video_id, video_id)
data = self._parse_json(
self._html_search_regex(
r'window\.POST_DATA = { %s: ({.+?}) };\s*</script>' % video_id,
self._search_regex(
r'window\.POST_DATA\s*=\s*{\s*%s\s*:\s*({.+?})\s*};\s*</script>' % video_id,
webpage, 'vine data'),
video_id)
formats = [{
'format_id': '%(format)s-%(rate)s' % f,
'vcodec': f['format'],
'quality': f['rate'],
'vcodec': f.get('format'),
'quality': f.get('rate'),
'url': f['videoUrl'],
} for f in data['videoUrls']]
} for f in data['videoUrls'] if f.get('videoUrl')]
self._sort_formats(formats)
username = data.get('username')
return {
'id': video_id,
'title': self._og_search_title(webpage),
'alt_title': self._og_search_description(webpage, default=None),
'description': data['description'],
'thumbnail': data['thumbnailUrl'],
'upload_date': unified_strdate(data['created']),
'uploader': data['username'],
'uploader_id': data['userIdStr'],
'like_count': data['likes']['count'],
'comment_count': data['comments']['count'],
'repost_count': data['reposts']['count'],
'title': data.get('description') or self._og_search_title(webpage),
'alt_title': 'Vine by %s' % username if username else self._og_search_description(webpage, default=None),
'thumbnail': data.get('thumbnailUrl'),
'upload_date': unified_strdate(data.get('created')),
'uploader': username,
'uploader_id': data.get('userIdStr'),
'like_count': int_or_none(data.get('likes', {}).get('count')),
'comment_count': int_or_none(data.get('comments', {}).get('count')),
'repost_count': int_or_none(data.get('reposts', {}).get('count')),
'formats': formats,
}

10
youtube_dl/extractor/vk.py
View File

@ -281,9 +281,13 @@ class VKIE(InfoExtractor):
mobj.group(1) + ' ' + mobj.group(2)
upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
view_count = str_to_int(self._search_regex(
r'"mv_views_count_number"[^>]*>([\d,.]+) views<',
info_page, 'view count', fatal=False))
view_count = None
views = self._html_search_regex(
r'"mv_views_count_number"[^>]*>(.+?\bviews?)<',
info_page, 'view count', fatal=False)
if views:
view_count = str_to_int(self._search_regex(
r'([\d,.]+)', views, 'view count', fatal=False))
formats = [{
'format_id': k,

214
youtube_dl/extractor/youporn.py
View File

@ -1,121 +1,171 @@
from __future__ import unicode_literals
import json
import re
import sys
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlparse,
compat_urllib_request,
)
from ..compat import compat_urllib_request
from ..utils import (
ExtractorError,
int_or_none,
str_to_int,
unescapeHTML,
unified_strdate,
)
from ..aes import (
aes_decrypt_text
)
from ..aes import aes_decrypt_text
class YouPornIE(InfoExtractor):
_VALID_URL = r'^(?P<proto>https?://)(?:www\.)?(?P<url>youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+))'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?youporn\.com/watch/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
'md5': '71ec5fcfddacf80f495efa8b6a8d9a89',
'info_dict': {
'id': '505835',
'display_id': 'sex-ed-is-it-safe-to-masturbate-daily',
'ext': 'mp4',
'upload_date': '20101221',
'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
'uploader': 'Ask Dan And Jennifer',
'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': 'Ask Dan And Jennifer',
'upload_date': '20101221',
'average_rating': int,
'view_count': int,
'comment_count': int,
'categories': list,
'tags': list,
'age_limit': 18,
}
}
},
}, {
# Anonymous User uploader
'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
'info_dict': {
'id': '561726',
'display_id': 'big-tits-awesome-brunette-on-amazing-webcam-show',
'ext': 'mp4',
'title': 'Big Tits Awesome Brunette On amazing webcam show',
'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': 'Anonymous User',
'upload_date': '20111125',
'average_rating': int,
'view_count': int,
'comment_count': int,
'categories': list,
'tags': list,
'age_limit': 18,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid')
url = mobj.group('proto') + 'www.' + mobj.group('url')
video_id = mobj.group('id')
display_id = mobj.group('display_id')
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
age_limit = self._rta_search(webpage)
request = compat_urllib_request.Request(url)
request.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(request, display_id)
# Get JSON parameters
json_params = self._search_regex(
[r'videoJa?son\s*=\s*({.+})',
r'var\s+currentVideo\s*=\s*new\s+Video\((.+?)\)[,;]'],
webpage, 'JSON parameters')
try:
params = json.loads(json_params)
except ValueError:
raise ExtractorError('Invalid JSON')
title = self._search_regex(
[r'(?:video_titles|videoTitle)\s*[:=]\s*(["\'])(?P<title>.+?)\1',
r'<h1[^>]+class=["\']heading\d?["\'][^>]*>([^<])<'],
webpage, 'title', group='title')
self.report_extraction(video_id)
try:
video_title = params['title']
upload_date = unified_strdate(params['release_date_f'])
video_description = params['description']
video_uploader = params['submitted_by']
thumbnail = params['thumbnails'][0]['image']
except KeyError:
raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
links = []
# Get all of the links from the page
DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
download_list_html = self._search_regex(DOWNLOAD_LIST_RE,
webpage, 'download list').strip()
LINK_RE = r'<a href="([^"]+)">'
links = re.findall(LINK_RE, download_list_html)
sources = self._search_regex(
r'sources\s*:\s*({.+?})', webpage, 'sources', default=None)
if sources:
for _, link in re.findall(r'[^:]+\s*:\s*(["\'])(http.+?)\1', sources):
links.append(link)
# Get all encrypted links
encrypted_links = re.findall(r'var encryptedQuality[0-9]{3}URL = \'([a-zA-Z0-9+/]+={0,2})\';', webpage)
for encrypted_link in encrypted_links:
link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8')
# Fallback #1
for _, link in re.findall(
r'(?:videoUrl|videoSrc|videoIpadUrl|html5PlayerSrc)\s*[:=]\s*(["\'])(http.+?)\1', webpage):
links.append(link)
# Fallback #2, this also contains extra low quality 180p format
for _, link in re.findall(r'<a[^>]+href=(["\'])(http.+?)\1[^>]+title=["\']Download [Vv]ideo', webpage):
links.append(link)
# Fallback #3, encrypted links
for _, encrypted_link in re.findall(
r'encryptedQuality\d{3,4}URL\s*=\s*(["\'])([\da-zA-Z+/=]+)\1', webpage):
links.append(aes_decrypt_text(encrypted_link, title, 32).decode('utf-8'))
formats = []
for link in links:
# A link looks like this:
# http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0
# A path looks like this:
# /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
video_url = unescapeHTML(link)
path = compat_urllib_parse_urlparse(video_url).path
format_parts = path.split('/')[4].split('_')[:2]
dn = compat_urllib_parse_urlparse(video_url).netloc.partition('.')[0]
resolution = format_parts[0]
height = int(resolution[:-len('p')])
bitrate = int(format_parts[1][:-len('k')])
format = '-'.join(format_parts) + '-' + dn
formats.append({
for video_url in set(unescapeHTML(link) for link in links):
f = {
'url': video_url,
'format': format,
'format_id': format,
'height': height,
'tbr': bitrate,
'resolution': resolution,
})
}
# Video URL's path looks like this:
# /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
# We will benefit from it by extracting some metadata
mobj = re.search(r'/(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+/', video_url)
if mobj:
height = int(mobj.group('height'))
bitrate = int(mobj.group('bitrate'))
f.update({
'format_id': '%dp-%dk' % (height, bitrate),
'height': height,
'tbr': bitrate,
})
formats.append(f)
self._sort_formats(formats)
if not formats:
raise ExtractorError('ERROR: no known formats available for video')
description = self._html_search_regex(
r'(?s)<div[^>]+class=["\']video-description["\'][^>]*>(.+?)</div>',
webpage, 'description', default=None)
thumbnail = self._search_regex(
r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
webpage, 'thumbnail', fatal=False, group='thumbnail')
uploader = self._html_search_regex(
r'(?s)<div[^>]+class=["\']videoInfoBy["\'][^>]*>\s*By:\s*</div>(.+?)</(?:a|div)>',
webpage, 'uploader', fatal=False)
upload_date = unified_strdate(self._html_search_regex(
r'(?s)<div[^>]+class=["\']videoInfoTime["\'][^>]*>(.+?)</div>',
webpage, 'upload date', fatal=False))
age_limit = self._rta_search(webpage)
average_rating = int_or_none(self._search_regex(
r'<div[^>]+class=["\']videoInfoRating["\'][^>]*>\s*<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>',
webpage, 'average rating', fatal=False))
view_count = str_to_int(self._search_regex(
r'(?s)<div[^>]+class=["\']videoInfoViews["\'][^>]*>.*?([\d,.]+)\s*</div>',
webpage, 'view count', fatal=False))
comment_count = str_to_int(self._search_regex(
r'>All [Cc]omments? \(([\d,.]+)\)',
webpage, 'comment count', fatal=False))
def extract_tag_box(title):
tag_box = self._search_regex(
(r'<div[^>]+class=["\']tagBoxTitle["\'][^>]*>\s*%s\b.*?</div>\s*'
'<div[^>]+class=["\']tagBoxContent["\']>(.+?)</div>') % re.escape(title),
webpage, '%s tag box' % title, default=None)
if not tag_box:
return []
return re.findall(r'<a[^>]+href=[^>]+>([^<]+)', tag_box)
categories = extract_tag_box('Category')
tags = extract_tag_box('Tags')
return {
'id': video_id,
'uploader': video_uploader,
'upload_date': upload_date,
'title': video_title,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'description': video_description,
'uploader': uploader,
'upload_date': upload_date,
'average_rating': average_rating,
'view_count': view_count,
'comment_count': comment_count,
'categories': categories,
'tags': tags,
'age_limit': age_limit,
'formats': formats,
}

146
youtube_dl/extractor/youtube.py
View File

@ -178,6 +178,52 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
return
class YoutubePlaylistBaseInfoExtractor(InfoExtractor):
# Extract the video ids from the playlist pages
def _entries(self, page, playlist_id):
more_widget_html = content_html = page
for page_num in itertools.count(1):
for video_id, video_title in self.extract_videos_from_page(content_html):
yield self.url_result(
video_id, 'Youtube', video_id=video_id,
video_title=video_title)
mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
if not mobj:
break
more = self._download_json(
'https://youtube.com/%s' % mobj.group('more'), playlist_id,
'Downloading page #%s' % page_num,
transform_source=uppercase_escape)
content_html = more['content_html']
if not content_html.strip():
# Some webpages show a "Load more" button but they don't
# have more videos
break
more_widget_html = more['load_more_widget_html']
def extract_videos_from_page(self, page):
ids_in_page = []
titles_in_page = []
for mobj in re.finditer(self._VIDEO_RE, page):
# The link with index 0 is not the first video of the playlist (not sure if still actual)
if 'index' in mobj.groupdict() and mobj.group('id') == '0':
continue
video_id = mobj.group('id')
video_title = unescapeHTML(mobj.group('title'))
if video_title:
video_title = video_title.strip()
try:
idx = ids_in_page.index(video_id)
if video_title and not titles_in_page[idx]:
titles_in_page[idx] = video_title
except ValueError:
ids_in_page.append(video_id)
titles_in_page.append(video_title)
return zip(ids_in_page, titles_in_page)
class YoutubeIE(YoutubeBaseInfoExtractor):
IE_DESC = 'YouTube.com'
_VALID_URL = r"""(?x)^
@ -1061,6 +1107,17 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if not video_info:
video_info = get_video_info
if 'token' in get_video_info:
# Different get_video_info requests may report different results, e.g.
# some may report video unavailability, but some may serve it without
# any complaint (see https://github.com/rg3/youtube-dl/issues/7362,
# the original webpage as well as el=info and el=embedded get_video_info
# requests report video unavailability due to geo restriction while
# el=detailpage succeeds and returns valid data). This is probably
# due to YouTube measures against IP ranges of hosting providers.
# Working around by preferring the first succeeded video_info containing
# the token if no such video_info yet was found.
if 'token' not in video_info:
video_info = get_video_info
break
if 'token' not in video_info:
if 'reason' in video_info:
@ -1419,7 +1476,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
}
class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
class YoutubePlaylistIE(YoutubeBaseInfoExtractor, YoutubePlaylistBaseInfoExtractor):
IE_DESC = 'YouTube.com playlists'
_VALID_URL = r"""(?x)(?:
(?:https?://)?
@ -1440,7 +1497,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
((?:PL|LL|EC|UU|FL|RD|UL)[0-9A-Za-z-_]{10,})
)"""
_TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
_VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)'
_VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
IE_NAME = 'youtube:playlist'
_TESTS = [{
'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
@ -1557,37 +1614,11 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
else:
self.report_warning('Youtube gives an alert message: ' + match)
# Extract the video ids from the playlist pages
def _entries():
more_widget_html = content_html = page
for page_num in itertools.count(1):
matches = re.finditer(self._VIDEO_RE, content_html)
# We remove the duplicates and the link with index 0
# (it's not the first video of the playlist)
new_ids = orderedSet(m.group('id') for m in matches if m.group('index') != '0')
for vid_id in new_ids:
yield self.url_result(vid_id, 'Youtube', video_id=vid_id)
mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
if not mobj:
break
more = self._download_json(
'https://youtube.com/%s' % mobj.group('more'), playlist_id,
'Downloading page #%s' % page_num,
transform_source=uppercase_escape)
content_html = more['content_html']
if not content_html.strip():
# Some webpages show a "Load more" button but they don't
# have more videos
break
more_widget_html = more['load_more_widget_html']
playlist_title = self._html_search_regex(
r'(?s)<h1 class="pl-header-title[^"]*">\s*(.*?)\s*</h1>',
page, 'title')
return self.playlist_result(_entries(), playlist_id, playlist_title)
return self.playlist_result(self._entries(page, playlist_id), playlist_id, playlist_title)
def _real_extract(self, url):
# Extract playlist id
@ -1613,36 +1644,31 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
return self._extract_playlist(playlist_id)
class YoutubeChannelIE(InfoExtractor):
class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
IE_DESC = 'YouTube.com channels'
_VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)'
_TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
_VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
IE_NAME = 'youtube:channel'
_TESTS = [{
'note': 'paginated channel',
'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
'playlist_mincount': 91,
'info_dict': {
'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
'title': 'Uploads from lex will',
}
}, {
'note': 'Age restricted channel',
# from https://www.youtube.com/user/DeusExOfficial
'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
'playlist_mincount': 64,
'info_dict': {
'id': 'UUs0ifCMCm1icqRbqhUINa0w',
'title': 'Uploads from Deus Ex',
},
}]
@staticmethod
def extract_videos_from_page(page):
ids_in_page = []
titles_in_page = []
for mobj in re.finditer(r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?', page):
video_id = mobj.group('id')
video_title = unescapeHTML(mobj.group('title'))
try:
idx = ids_in_page.index(video_id)
if video_title and not titles_in_page[idx]:
titles_in_page[idx] = video_title
except ValueError:
ids_in_page.append(video_id)
titles_in_page.append(video_title)
return zip(ids_in_page, titles_in_page)
def _real_extract(self, url):
channel_id = self._match_id(url)
@ -1661,7 +1687,7 @@ class YoutubeChannelIE(InfoExtractor):
'channelId', channel_page, 'channel id', default=None)
if not channel_playlist_id:
channel_playlist_id = self._search_regex(
r'data-channel-external-id="([^"]+)"',
r'data-(?:channel-external-|yt)id="([^"]+)"',
channel_page, 'channel id', default=None)
if channel_playlist_id and channel_playlist_id.startswith('UC'):
playlist_id = 'UU' + channel_playlist_id[2:]
@ -1685,29 +1711,7 @@ class YoutubeChannelIE(InfoExtractor):
for video_id, video_title in self.extract_videos_from_page(channel_page)]
return self.playlist_result(entries, channel_id)
def _entries():
more_widget_html = content_html = channel_page
for pagenum in itertools.count(1):
for video_id, video_title in self.extract_videos_from_page(content_html):
yield self.url_result(
video_id, 'Youtube', video_id=video_id,
video_title=video_title)
mobj = re.search(
r'data-uix-load-more-href="/?(?P<more>[^"]+)"',
more_widget_html)
if not mobj:
break
more = self._download_json(
'https://youtube.com/%s' % mobj.group('more'), channel_id,
'Downloading page #%s' % (pagenum + 1),
transform_source=uppercase_escape)
content_html = more['content_html']
more_widget_html = more['load_more_widget_html']
return self.playlist_result(_entries(), channel_id)
return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
class YoutubeUserIE(YoutubeChannelIE):

50
youtube_dl/extractor/zdf.py
View File

@ -9,6 +9,7 @@ from ..utils import (
int_or_none,
unified_strdate,
OnDemandPagedList,
xpath_text,
)
@ -19,13 +20,11 @@ def extract_from_xml_url(ie, video_id, xml_url):
errnote='Failed to download video info')
title = doc.find('.//information/title').text
description = doc.find('.//information/detail').text
duration = int(doc.find('.//details/lengthSec').text)
uploader_node = doc.find('.//details/originChannelTitle')
uploader = None if uploader_node is None else uploader_node.text
uploader_id_node = doc.find('.//details/originChannelId')
uploader_id = None if uploader_id_node is None else uploader_id_node.text
upload_date = unified_strdate(doc.find('.//details/airtime').text)
description = xpath_text(doc, './/information/detail', 'description')
duration = int_or_none(xpath_text(doc, './/details/lengthSec', 'duration'))
uploader = xpath_text(doc, './/details/originChannelTitle', 'uploader')
uploader_id = xpath_text(doc, './/details/originChannelId', 'uploader id')
upload_date = unified_strdate(xpath_text(doc, './/details/airtime', 'upload date'))
def xml_to_format(fnode):
video_url = fnode.find('url').text
@ -40,15 +39,14 @@ def extract_from_xml_url(ie, video_id, xml_url):
ext = format_m.group('container')
proto = format_m.group('proto').lower()
quality = fnode.find('./quality').text
abr = int(fnode.find('./audioBitrate').text) // 1000
vbr_node = fnode.find('./videoBitrate')
vbr = None if vbr_node is None else int(vbr_node.text) // 1000
quality = xpath_text(fnode, './quality', 'quality')
abr = int_or_none(xpath_text(fnode, './audioBitrate', 'abr'), 1000)
vbr = int_or_none(xpath_text(fnode, './videoBitrate', 'vbr'), 1000)
width_node = fnode.find('./width')
width = None if width_node is None else int_or_none(width_node.text)
height_node = fnode.find('./height')
height = None if height_node is None else int_or_none(height_node.text)
width = int_or_none(xpath_text(fnode, './width', 'width'))
height = int_or_none(xpath_text(fnode, './height', 'height'))
filesize = int_or_none(xpath_text(fnode, './filesize', 'filesize'))
format_note = ''
if not format_note:
@ -64,12 +62,31 @@ def extract_from_xml_url(ie, video_id, xml_url):
'vbr': vbr,
'width': width,
'height': height,
'filesize': int_or_none(fnode.find('./filesize').text),
'filesize': filesize,
'format_note': format_note,
'protocol': proto,
'_available': is_available,
}
def xml_to_thumbnails(fnode):
thumbnails = []
for node in fnode:
thumbnail_url = node.text
if not thumbnail_url:
continue
thumbnail = {
'url': thumbnail_url,
}
if 'key' in node.attrib:
m = re.match('^([0-9]+)x([0-9]+)$', node.attrib['key'])
if m:
thumbnail['width'] = int(m.group(1))
thumbnail['height'] = int(m.group(2))
thumbnails.append(thumbnail)
return thumbnails
thumbnails = xml_to_thumbnails(doc.findall('.//teaserimages/teaserimage'))
format_nodes = doc.findall('.//formitaeten/formitaet')
formats = list(filter(
lambda f: f['_available'],
@ -81,6 +98,7 @@ def extract_from_xml_url(ie, video_id, xml_url):
'title': title,
'description': description,
'duration': duration,
'thumbnails': thumbnails,
'uploader': uploader,
'uploader_id': uploader_id,
'upload_date': upload_date,

2
youtube_dl/postprocessor/ffmpeg.py
View File

@ -272,7 +272,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
return [], information
try:
self._downloader.to_screen('[' + self.basename + '] Destination: ' + new_path)
self._downloader.to_screen('[ffmpeg] Destination: ' + new_path)
self.run_ffmpeg(path, new_path, acodec, more_opts)
except AudioConversionError as e:
raise PostProcessingError(

68
youtube_dl/utils.py
View File

@ -3,6 +3,7 @@
from __future__ import unicode_literals
import base64
import calendar
import codecs
import contextlib
@ -35,6 +36,7 @@ import zlib
from .compat import (
compat_basestring,
compat_chr,
compat_etree_fromstring,
compat_html_entities,
compat_http_client,
compat_kwargs,
@ -177,10 +179,19 @@ def xpath_with_ns(path, ns_map):
def xpath_element(node, xpath, name=None, fatal=False, default=NO_DEFAULT):
if sys.version_info < (2, 7): # Crazy 2.6
xpath = xpath.encode('ascii')
def _find_xpath(xpath):
if sys.version_info < (2, 7): # Crazy 2.6
xpath = xpath.encode('ascii')
return node.find(xpath)
if isinstance(xpath, (str, compat_str)):
n = _find_xpath(xpath)
else:
for xp in xpath:
n = _find_xpath(xp)
if n is not None:
break
n = node.find(xpath)
if n is None:
if default is not NO_DEFAULT:
return default
@ -355,7 +366,7 @@ def sanitize_path(s):
if drive_or_unc:
norm_path.pop(0)
sanitized_path = [
path_part if path_part in ['.', '..'] else re.sub('(?:[/<>:"\\|\\\\?\\*]|\.$)', '#', path_part)
path_part if path_part in ['.', '..'] else re.sub('(?:[/<>:"\\|\\\\?\\*]|[\s.]$)', '#', path_part)
for path_part in norm_path]
if drive_or_unc:
sanitized_path.insert(0, drive_or_unc + os.path.sep)
@ -813,9 +824,11 @@ def parse_iso8601(date_str, delimiter='T', timezone=None):
if date_str is None:
return None
date_str = re.sub(r'\.[0-9]+', '', date_str)
if timezone is None:
m = re.search(
r'(\.[0-9]+)?(?:Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$)',
r'(?:Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$)',
date_str)
if not m:
timezone = datetime.timedelta()
@ -828,9 +841,12 @@ def parse_iso8601(date_str, delimiter='T', timezone=None):
timezone = datetime.timedelta(
hours=sign * int(m.group('hours')),
minutes=sign * int(m.group('minutes')))
date_format = '%Y-%m-%d{0}%H:%M:%S'.format(delimiter)
dt = datetime.datetime.strptime(date_str, date_format) - timezone
return calendar.timegm(dt.timetuple())
try:
date_format = '%Y-%m-%d{0}%H:%M:%S'.format(delimiter)
dt = datetime.datetime.strptime(date_str, date_format) - timezone
return calendar.timegm(dt.timetuple())
except ValueError:
pass
def unified_strdate(date_str, day_first=True):
@ -895,7 +911,8 @@ def unified_strdate(date_str, day_first=True):
timetuple = email.utils.parsedate_tz(date_str)
if timetuple:
upload_date = datetime.datetime(*timetuple[:6]).strftime('%Y%m%d')
return upload_date
if upload_date is not None:
return compat_str(upload_date)
def determine_ext(url, default_ext='unknown_video'):
@ -1650,29 +1667,6 @@ def encode_dict(d, encoding='utf-8'):
return dict((k.encode(encoding), v.encode(encoding)) for k, v in d.items())
try:
etree_iter = xml.etree.ElementTree.Element.iter
except AttributeError: # Python <=2.6
etree_iter = lambda n: n.findall('.//*')
def parse_xml(s):
class TreeBuilder(xml.etree.ElementTree.TreeBuilder):
def doctype(self, name, pubid, system):
pass # Ignore doctypes
parser = xml.etree.ElementTree.XMLParser(target=TreeBuilder())
kwargs = {'parser': parser} if sys.version_info >= (2, 7) else {}
tree = xml.etree.ElementTree.XML(s.encode('utf-8'), **kwargs)
# Fix up XML parser in Python 2.x
if sys.version_info < (3, 0):
for n in etree_iter(tree):
if n.text is not None:
if not isinstance(n.text, compat_str):
n.text = n.text.decode('utf-8')
return tree
US_RATINGS = {
'G': 0,
'PG': 10,
@ -1700,8 +1694,8 @@ def js_to_json(code):
if v in ('true', 'false', 'null'):
return v
if v.startswith('"'):
return v
if v.startswith("'"):
v = re.sub(r"\\'", "'", v[1:-1])
elif v.startswith("'"):
v = v[1:-1]
v = re.sub(r"\\\\|\\'|\"", lambda m: {
'\\\\': '\\\\',
@ -1795,6 +1789,10 @@ def urlhandle_detect_ext(url_handle):
return mimetype2ext(getheader('Content-Type'))
def encode_data_uri(data, mime_type):
return 'data:%s;base64,%s' % (mime_type, base64.b64encode(data).decode('ascii'))
def age_restricted(content_limit, age_limit):
""" Returns True iff the content should be blocked """
@ -1969,7 +1967,7 @@ def dfxp2srt(dfxp_data):
return out
dfxp = xml.etree.ElementTree.fromstring(dfxp_data.encode('utf-8'))
dfxp = compat_etree_fromstring(dfxp_data.encode('utf-8'))
out = []
paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall(_x('.//ttaf1:p')) or dfxp.findall('.//p')

2
youtube_dl/version.py
View File

@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2015.10.13'
__version__ = '2015.11.02'