mirror of
https://github.com/l1ving/youtube-dl
synced 2025-03-09 21:57:14 +08:00
Merge pull request #309 from ytdl-org/master
[pull] master from ytdl-org:master
This commit is contained in:
commit
047ce5bac3
@ -39,6 +39,13 @@ class TestYoutubeDLCookieJar(unittest.TestCase):
|
||||
assert_cookie_has_value('HTTPONLY_COOKIE')
|
||||
assert_cookie_has_value('JS_ACCESSIBLE_COOKIE')
|
||||
|
||||
def test_malformed_cookies(self):
|
||||
cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/malformed_cookies.txt')
|
||||
cookiejar.load(ignore_discard=True, ignore_expires=True)
|
||||
# Cookies should be empty since all malformed cookie file entries
|
||||
# will be ignored
|
||||
self.assertFalse(cookiejar._cookies)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
9
test/testdata/cookies/malformed_cookies.txt
vendored
Normal file
9
test/testdata/cookies/malformed_cookies.txt
vendored
Normal file
@ -0,0 +1,9 @@
|
||||
# Netscape HTTP Cookie File
|
||||
# http://curl.haxx.se/rfc/cookie_spec.html
|
||||
# This is a generated file! Do not edit.
|
||||
|
||||
# Cookie file entry with invalid number of fields - 6 instead of 7
|
||||
www.foobar.foobar FALSE / FALSE 0 COOKIE
|
||||
|
||||
# Cookie file entry with invalid expires at
|
||||
www.foobar.foobar FALSE / FALSE 1.7976931348623157e+308 COOKIE VALUE
|
@ -57,6 +57,17 @@ try:
|
||||
except ImportError: # Python 2
|
||||
import cookielib as compat_cookiejar
|
||||
|
||||
if sys.version_info[0] == 2:
|
||||
class compat_cookiejar_Cookie(compat_cookiejar.Cookie):
|
||||
def __init__(self, version, name, value, *args, **kwargs):
|
||||
if isinstance(name, compat_str):
|
||||
name = name.encode()
|
||||
if isinstance(value, compat_str):
|
||||
value = value.encode()
|
||||
compat_cookiejar.Cookie.__init__(self, version, name, value, *args, **kwargs)
|
||||
else:
|
||||
compat_cookiejar_Cookie = compat_cookiejar.Cookie
|
||||
|
||||
try:
|
||||
import http.cookies as compat_cookies
|
||||
except ImportError: # Python 2
|
||||
@ -2987,6 +2998,7 @@ __all__ = [
|
||||
'compat_basestring',
|
||||
'compat_chr',
|
||||
'compat_cookiejar',
|
||||
'compat_cookiejar_Cookie',
|
||||
'compat_cookies',
|
||||
'compat_ctypes_WINFUNCTYPE',
|
||||
'compat_etree_Element',
|
||||
|
@ -227,7 +227,7 @@ class HttpFD(FileDownloader):
|
||||
while True:
|
||||
try:
|
||||
# Download and write
|
||||
data_block = ctx.data.read(block_size if not is_test else min(block_size, data_len - byte_counter))
|
||||
data_block = ctx.data.read(block_size if data_len is None else min(block_size, data_len - byte_counter))
|
||||
# socket.timeout is a subclass of socket.error but may not have
|
||||
# errno set
|
||||
except socket.timeout as e:
|
||||
@ -299,7 +299,7 @@ class HttpFD(FileDownloader):
|
||||
'elapsed': now - ctx.start_time,
|
||||
})
|
||||
|
||||
if is_test and byte_counter == data_len:
|
||||
if data_len is not None and byte_counter == data_len:
|
||||
break
|
||||
|
||||
if not is_test and ctx.chunk_size and ctx.data_len is not None and byte_counter < ctx.data_len:
|
||||
|
@ -15,7 +15,7 @@ import time
|
||||
import math
|
||||
|
||||
from ..compat import (
|
||||
compat_cookiejar,
|
||||
compat_cookiejar_Cookie,
|
||||
compat_cookies,
|
||||
compat_etree_Element,
|
||||
compat_etree_fromstring,
|
||||
@ -2843,7 +2843,7 @@ class InfoExtractor(object):
|
||||
|
||||
def _set_cookie(self, domain, name, value, expire_time=None, port=None,
|
||||
path='/', secure=False, discard=False, rest={}, **kwargs):
|
||||
cookie = compat_cookiejar.Cookie(
|
||||
cookie = compat_cookiejar_Cookie(
|
||||
0, name, value, port, port is not None, domain, True,
|
||||
domain.startswith('.'), path, True, secure, expire_time,
|
||||
discard, None, None, rest)
|
||||
|
@ -32,7 +32,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
|
||||
|
||||
@staticmethod
|
||||
def _get_cookie_value(cookies, name):
|
||||
cookie = cookies.get('name')
|
||||
cookie = cookies.get(name)
|
||||
if cookie:
|
||||
return cookie.value
|
||||
|
||||
|
@ -804,6 +804,16 @@ from .orf import (
|
||||
ORFFM4IE,
|
||||
ORFFM4StoryIE,
|
||||
ORFOE1IE,
|
||||
ORFOE3IE,
|
||||
ORFNOEIE,
|
||||
ORFWIEIE,
|
||||
ORFBGLIE,
|
||||
ORFOOEIE,
|
||||
ORFSTMIE,
|
||||
ORFKTNIE,
|
||||
ORFSBGIE,
|
||||
ORFTIRIE,
|
||||
ORFVBGIE,
|
||||
ORFIPTVIE,
|
||||
)
|
||||
from .outsidetv import OutsideTVIE
|
||||
|
@ -16,12 +16,22 @@ class IPrimaIE(InfoExtractor):
|
||||
_GEO_BYPASS = False
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://play.iprima.cz/gondici-s-r-o-33',
|
||||
'url': 'https://prima.iprima.cz/particka/92-epizoda',
|
||||
'info_dict': {
|
||||
'id': 'p136534',
|
||||
'id': 'p51388',
|
||||
'ext': 'mp4',
|
||||
'title': 'Gondíci s. r. o. (34)',
|
||||
'description': 'md5:16577c629d006aa91f59ca8d8e7f99bd',
|
||||
'title': 'Partička (92)',
|
||||
'description': 'md5:859d53beae4609e6dd7796413f1b6cac',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True, # m3u8 download
|
||||
},
|
||||
}, {
|
||||
'url': 'https://cnn.iprima.cz/videa/70-epizoda',
|
||||
'info_dict': {
|
||||
'id': 'p681554',
|
||||
'ext': 'mp4',
|
||||
'title': 'HLAVNÍ ZPRÁVY 3.5.2020',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True, # m3u8 download
|
||||
@ -68,9 +78,15 @@ class IPrimaIE(InfoExtractor):
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
title = self._og_search_title(
|
||||
webpage, default=None) or self._search_regex(
|
||||
r'<h1>([^<]+)', webpage, 'title')
|
||||
|
||||
video_id = self._search_regex(
|
||||
(r'<iframe[^>]+\bsrc=["\'](?:https?:)?//(?:api\.play-backend\.iprima\.cz/prehravac/embedded|prima\.iprima\.cz/[^/]+/[^/]+)\?.*?\bid=(p\d+)',
|
||||
r'data-product="([^"]+)">'),
|
||||
r'data-product="([^"]+)">',
|
||||
r'id=["\']player-(p\d+)"',
|
||||
r'playerId\s*:\s*["\']player-(p\d+)'),
|
||||
webpage, 'real id')
|
||||
|
||||
playerpage = self._download_webpage(
|
||||
@ -125,8 +141,8 @@ class IPrimaIE(InfoExtractor):
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': self._og_search_title(webpage),
|
||||
'thumbnail': self._og_search_thumbnail(webpage),
|
||||
'title': title,
|
||||
'thumbnail': self._og_search_thumbnail(webpage, default=None),
|
||||
'formats': formats,
|
||||
'description': self._og_search_description(webpage),
|
||||
'description': self._og_search_description(webpage, default=None),
|
||||
}
|
||||
|
@ -162,13 +162,12 @@ class ORFTVthekIE(InfoExtractor):
|
||||
class ORFRadioIE(InfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
station = mobj.group('station')
|
||||
show_date = mobj.group('date')
|
||||
show_id = mobj.group('show')
|
||||
|
||||
data = self._download_json(
|
||||
'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s'
|
||||
% (station, show_id, show_date), show_id)
|
||||
% (self._API_STATION, show_id, show_date), show_id)
|
||||
|
||||
entries = []
|
||||
for info in data['streams']:
|
||||
@ -183,7 +182,7 @@ class ORFRadioIE(InfoExtractor):
|
||||
duration = end - start if end and start else None
|
||||
entries.append({
|
||||
'id': loop_stream_id.replace('.mp3', ''),
|
||||
'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (station, loop_stream_id),
|
||||
'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (self._LOOP_STATION, loop_stream_id),
|
||||
'title': title,
|
||||
'description': clean_html(data.get('subtitle')),
|
||||
'duration': duration,
|
||||
@ -205,6 +204,8 @@ class ORFFM4IE(ORFRadioIE):
|
||||
IE_NAME = 'orf:fm4'
|
||||
IE_DESC = 'radio FM4'
|
||||
_VALID_URL = r'https?://(?P<station>fm4)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>4\w+)'
|
||||
_API_STATION = 'fm4'
|
||||
_LOOP_STATION = 'fm4'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://fm4.orf.at/player/20170107/4CC',
|
||||
@ -223,10 +224,142 @@ class ORFFM4IE(ORFRadioIE):
|
||||
}
|
||||
|
||||
|
||||
class ORFNOEIE(ORFRadioIE):
|
||||
IE_NAME = 'orf:noe'
|
||||
IE_DESC = 'Radio Niederösterreich'
|
||||
_VALID_URL = r'https?://(?P<station>noe)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
|
||||
_API_STATION = 'noe'
|
||||
_LOOP_STATION = 'oe2n'
|
||||
|
||||
_TEST = {
|
||||
'url': 'https://noe.orf.at/player/20200423/NGM',
|
||||
'only_matching': True,
|
||||
}
|
||||
|
||||
|
||||
class ORFWIEIE(ORFRadioIE):
|
||||
IE_NAME = 'orf:wien'
|
||||
IE_DESC = 'Radio Wien'
|
||||
_VALID_URL = r'https?://(?P<station>wien)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
|
||||
_API_STATION = 'wie'
|
||||
_LOOP_STATION = 'oe2w'
|
||||
|
||||
_TEST = {
|
||||
'url': 'https://wien.orf.at/player/20200423/WGUM',
|
||||
'only_matching': True,
|
||||
}
|
||||
|
||||
|
||||
class ORFBGLIE(ORFRadioIE):
|
||||
IE_NAME = 'orf:burgenland'
|
||||
IE_DESC = 'Radio Burgenland'
|
||||
_VALID_URL = r'https?://(?P<station>burgenland)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
|
||||
_API_STATION = 'bgl'
|
||||
_LOOP_STATION = 'oe2b'
|
||||
|
||||
_TEST = {
|
||||
'url': 'https://burgenland.orf.at/player/20200423/BGM',
|
||||
'only_matching': True,
|
||||
}
|
||||
|
||||
|
||||
class ORFOOEIE(ORFRadioIE):
|
||||
IE_NAME = 'orf:oberoesterreich'
|
||||
IE_DESC = 'Radio Oberösterreich'
|
||||
_VALID_URL = r'https?://(?P<station>ooe)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
|
||||
_API_STATION = 'ooe'
|
||||
_LOOP_STATION = 'oe2o'
|
||||
|
||||
_TEST = {
|
||||
'url': 'https://ooe.orf.at/player/20200423/OGMO',
|
||||
'only_matching': True,
|
||||
}
|
||||
|
||||
|
||||
class ORFSTMIE(ORFRadioIE):
|
||||
IE_NAME = 'orf:steiermark'
|
||||
IE_DESC = 'Radio Steiermark'
|
||||
_VALID_URL = r'https?://(?P<station>steiermark)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
|
||||
_API_STATION = 'stm'
|
||||
_LOOP_STATION = 'oe2st'
|
||||
|
||||
_TEST = {
|
||||
'url': 'https://steiermark.orf.at/player/20200423/STGMS',
|
||||
'only_matching': True,
|
||||
}
|
||||
|
||||
|
||||
class ORFKTNIE(ORFRadioIE):
|
||||
IE_NAME = 'orf:kaernten'
|
||||
IE_DESC = 'Radio Kärnten'
|
||||
_VALID_URL = r'https?://(?P<station>kaernten)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
|
||||
_API_STATION = 'ktn'
|
||||
_LOOP_STATION = 'oe2k'
|
||||
|
||||
_TEST = {
|
||||
'url': 'https://kaernten.orf.at/player/20200423/KGUMO',
|
||||
'only_matching': True,
|
||||
}
|
||||
|
||||
|
||||
class ORFSBGIE(ORFRadioIE):
|
||||
IE_NAME = 'orf:salzburg'
|
||||
IE_DESC = 'Radio Salzburg'
|
||||
_VALID_URL = r'https?://(?P<station>salzburg)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
|
||||
_API_STATION = 'sbg'
|
||||
_LOOP_STATION = 'oe2s'
|
||||
|
||||
_TEST = {
|
||||
'url': 'https://salzburg.orf.at/player/20200423/SGUM',
|
||||
'only_matching': True,
|
||||
}
|
||||
|
||||
|
||||
class ORFTIRIE(ORFRadioIE):
|
||||
IE_NAME = 'orf:tirol'
|
||||
IE_DESC = 'Radio Tirol'
|
||||
_VALID_URL = r'https?://(?P<station>tirol)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
|
||||
_API_STATION = 'tir'
|
||||
_LOOP_STATION = 'oe2t'
|
||||
|
||||
_TEST = {
|
||||
'url': 'https://tirol.orf.at/player/20200423/TGUMO',
|
||||
'only_matching': True,
|
||||
}
|
||||
|
||||
|
||||
class ORFVBGIE(ORFRadioIE):
|
||||
IE_NAME = 'orf:vorarlberg'
|
||||
IE_DESC = 'Radio Vorarlberg'
|
||||
_VALID_URL = r'https?://(?P<station>vorarlberg)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
|
||||
_API_STATION = 'vbg'
|
||||
_LOOP_STATION = 'oe2v'
|
||||
|
||||
_TEST = {
|
||||
'url': 'https://vorarlberg.orf.at/player/20200423/VGUM',
|
||||
'only_matching': True,
|
||||
}
|
||||
|
||||
|
||||
class ORFOE3IE(ORFRadioIE):
|
||||
IE_NAME = 'orf:oe3'
|
||||
IE_DESC = 'Radio Österreich 3'
|
||||
_VALID_URL = r'https?://(?P<station>oe3)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
|
||||
_API_STATION = 'oe3'
|
||||
_LOOP_STATION = 'oe3'
|
||||
|
||||
_TEST = {
|
||||
'url': 'https://oe3.orf.at/player/20200424/3WEK',
|
||||
'only_matching': True,
|
||||
}
|
||||
|
||||
|
||||
class ORFOE1IE(ORFRadioIE):
|
||||
IE_NAME = 'orf:oe1'
|
||||
IE_DESC = 'Radio Österreich 1'
|
||||
_VALID_URL = r'https?://(?P<station>oe1)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
|
||||
_API_STATION = 'oe1'
|
||||
_LOOP_STATION = 'oe1'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://oe1.orf.at/player/20170108/456544',
|
||||
|
@ -82,17 +82,6 @@ class PuhuTVIE(InfoExtractor):
|
||||
urls = []
|
||||
formats = []
|
||||
|
||||
def add_http_from_hls(m3u8_f):
|
||||
http_url = m3u8_f['url'].replace('/hls/', '/mp4/').replace('/chunklist.m3u8', '.mp4')
|
||||
if http_url != m3u8_f['url']:
|
||||
f = m3u8_f.copy()
|
||||
f.update({
|
||||
'format_id': f['format_id'].replace('hls', 'http'),
|
||||
'protocol': 'http',
|
||||
'url': http_url,
|
||||
})
|
||||
formats.append(f)
|
||||
|
||||
for video in videos['data']['videos']:
|
||||
media_url = url_or_none(video.get('url'))
|
||||
if not media_url or media_url in urls:
|
||||
@ -101,12 +90,9 @@ class PuhuTVIE(InfoExtractor):
|
||||
|
||||
playlist = video.get('is_playlist')
|
||||
if (video.get('stream_type') == 'hls' and playlist is True) or 'playlist.m3u8' in media_url:
|
||||
m3u8_formats = self._extract_m3u8_formats(
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
media_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
||||
m3u8_id='hls', fatal=False)
|
||||
for m3u8_f in m3u8_formats:
|
||||
formats.append(m3u8_f)
|
||||
add_http_from_hls(m3u8_f)
|
||||
m3u8_id='hls', fatal=False))
|
||||
continue
|
||||
|
||||
quality = int_or_none(video.get('quality'))
|
||||
@ -128,8 +114,6 @@ class PuhuTVIE(InfoExtractor):
|
||||
format_id += '-%sp' % quality
|
||||
f['format_id'] = format_id
|
||||
formats.append(f)
|
||||
if is_hls:
|
||||
add_http_from_hls(f)
|
||||
self._sort_formats(formats)
|
||||
|
||||
creator = try_get(
|
||||
|
@ -2,12 +2,17 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_str,
|
||||
compat_urllib_parse_urlencode,
|
||||
)
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
parse_iso8601,
|
||||
qualities,
|
||||
update_url_query,
|
||||
str_or_none,
|
||||
)
|
||||
|
||||
|
||||
@ -16,21 +21,25 @@ class UOLIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:.+?\.)?uol\.com\.br/.*?(?:(?:mediaId|v)=|view/(?:[a-z0-9]+/)?|video(?:=|/(?:\d{4}/\d{2}/\d{2}/)?))(?P<id>\d+|[\w-]+-[A-Z0-9]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://player.mais.uol.com.br/player_video_v3.swf?mediaId=15951931',
|
||||
'md5': '25291da27dc45e0afb5718a8603d3816',
|
||||
'md5': '4f1e26683979715ff64e4e29099cf020',
|
||||
'info_dict': {
|
||||
'id': '15951931',
|
||||
'ext': 'mp4',
|
||||
'title': 'Miss simpatia é encontrada morta',
|
||||
'description': 'md5:3f8c11a0c0556d66daf7e5b45ef823b2',
|
||||
'timestamp': 1470421860,
|
||||
'upload_date': '20160805',
|
||||
}
|
||||
}, {
|
||||
'url': 'http://tvuol.uol.com.br/video/incendio-destroi-uma-das-maiores-casas-noturnas-de-londres-04024E9A3268D4C95326',
|
||||
'md5': 'e41a2fb7b7398a3a46b6af37b15c00c9',
|
||||
'md5': '2850a0e8dfa0a7307e04a96c5bdc5bc2',
|
||||
'info_dict': {
|
||||
'id': '15954259',
|
||||
'ext': 'mp4',
|
||||
'title': 'Incêndio destrói uma das maiores casas noturnas de Londres',
|
||||
'description': 'Em Londres, um incêndio destruiu uma das maiores boates da cidade. Não há informações sobre vítimas.',
|
||||
'timestamp': 1470674520,
|
||||
'upload_date': '20160808',
|
||||
}
|
||||
}, {
|
||||
'url': 'http://mais.uol.com.br/static/uolplayer/index.html?mediaId=15951931',
|
||||
@ -55,91 +64,55 @@ class UOLIE(InfoExtractor):
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
_FORMATS = {
|
||||
'2': {
|
||||
'width': 640,
|
||||
'height': 360,
|
||||
},
|
||||
'5': {
|
||||
'width': 1280,
|
||||
'height': 720,
|
||||
},
|
||||
'6': {
|
||||
'width': 426,
|
||||
'height': 240,
|
||||
},
|
||||
'7': {
|
||||
'width': 1920,
|
||||
'height': 1080,
|
||||
},
|
||||
'8': {
|
||||
'width': 192,
|
||||
'height': 144,
|
||||
},
|
||||
'9': {
|
||||
'width': 568,
|
||||
'height': 320,
|
||||
},
|
||||
'11': {
|
||||
'width': 640,
|
||||
'height': 360,
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
media_id = None
|
||||
|
||||
if video_id.isdigit():
|
||||
media_id = video_id
|
||||
|
||||
if not media_id:
|
||||
embed_page = self._download_webpage(
|
||||
'https://jsuol.com.br/c/tv/uol/embed/?params=[embed,%s]' % video_id,
|
||||
video_id, 'Downloading embed page', fatal=False)
|
||||
if embed_page:
|
||||
media_id = self._search_regex(
|
||||
(r'uol\.com\.br/(\d+)', r'mediaId=(\d+)'),
|
||||
embed_page, 'media id', default=None)
|
||||
|
||||
if not media_id:
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
media_id = self._search_regex(r'mediaId=(\d+)', webpage, 'media id')
|
||||
|
||||
video_data = self._download_json(
|
||||
'http://mais.uol.com.br/apiuol/v3/player/getMedia/%s.json' % media_id,
|
||||
media_id)['item']
|
||||
# https://api.mais.uol.com.br/apiuol/v4/player/data/[MEDIA_ID]
|
||||
'https://api.mais.uol.com.br/apiuol/v3/media/detail/' + video_id,
|
||||
video_id)['item']
|
||||
media_id = compat_str(video_data['mediaId'])
|
||||
title = video_data['title']
|
||||
ver = video_data.get('revision', 2)
|
||||
|
||||
query = {
|
||||
'ver': video_data.get('numRevision', 2),
|
||||
'r': 'http://mais.uol.com.br',
|
||||
}
|
||||
for k in ('token', 'sign'):
|
||||
v = video_data.get(k)
|
||||
if v:
|
||||
query[k] = v
|
||||
|
||||
uol_formats = self._download_json(
|
||||
'https://croupier.mais.uol.com.br/v3/formats/%s/jsonp' % media_id,
|
||||
media_id)
|
||||
quality = qualities(['mobile', 'WEBM', '360p', '720p', '1080p'])
|
||||
formats = []
|
||||
for f in video_data.get('formats', []):
|
||||
for format_id, f in uol_formats.items():
|
||||
if not isinstance(f, dict):
|
||||
continue
|
||||
f_url = f.get('url') or f.get('secureUrl')
|
||||
if not f_url:
|
||||
continue
|
||||
query = {
|
||||
'ver': ver,
|
||||
'r': 'http://mais.uol.com.br',
|
||||
}
|
||||
for k in ('token', 'sign'):
|
||||
v = f.get(k)
|
||||
if v:
|
||||
query[k] = v
|
||||
f_url = update_url_query(f_url, query)
|
||||
format_id = str_or_none(f.get('id'))
|
||||
if format_id == '10':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
f_url, video_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id='hls', fatal=False))
|
||||
format_id = format_id
|
||||
if format_id == 'HLS':
|
||||
m3u8_formats = self._extract_m3u8_formats(
|
||||
f_url, media_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id='hls', fatal=False)
|
||||
encoded_query = compat_urllib_parse_urlencode(query)
|
||||
for m3u8_f in m3u8_formats:
|
||||
m3u8_f['extra_param_to_segment_url'] = encoded_query
|
||||
m3u8_f['url'] = update_url_query(m3u8_f['url'], query)
|
||||
formats.extend(m3u8_formats)
|
||||
continue
|
||||
fmt = {
|
||||
formats.append({
|
||||
'format_id': format_id,
|
||||
'url': f_url,
|
||||
'source_preference': 1,
|
||||
}
|
||||
fmt.update(self._FORMATS.get(format_id, {}))
|
||||
formats.append(fmt)
|
||||
self._sort_formats(formats, ('height', 'width', 'source_preference', 'tbr', 'ext'))
|
||||
'quality': quality(format_id),
|
||||
'preference': -1,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
tags = []
|
||||
for tag in video_data.get('tags', []):
|
||||
@ -148,12 +121,24 @@ class UOLIE(InfoExtractor):
|
||||
continue
|
||||
tags.append(tag_description)
|
||||
|
||||
thumbnails = []
|
||||
for q in ('Small', 'Medium', 'Wmedium', 'Large', 'Wlarge', 'Xlarge'):
|
||||
q_url = video_data.get('thumb' + q)
|
||||
if not q_url:
|
||||
continue
|
||||
thumbnails.append({
|
||||
'id': q,
|
||||
'url': q_url,
|
||||
})
|
||||
|
||||
return {
|
||||
'id': media_id,
|
||||
'title': title,
|
||||
'description': clean_html(video_data.get('desMedia')),
|
||||
'thumbnail': video_data.get('thumbnail'),
|
||||
'duration': int_or_none(video_data.get('durationSeconds')) or parse_duration(video_data.get('duration')),
|
||||
'description': clean_html(video_data.get('description')),
|
||||
'thumbnails': thumbnails,
|
||||
'duration': parse_duration(video_data.get('duration')),
|
||||
'tags': tags,
|
||||
'formats': formats,
|
||||
'timestamp': parse_iso8601(video_data.get('publishDate'), ' '),
|
||||
'view_count': int_or_none(video_data.get('viewsQtty')),
|
||||
}
|
||||
|
@ -7,6 +7,7 @@ import base64
|
||||
import binascii
|
||||
import calendar
|
||||
import codecs
|
||||
import collections
|
||||
import contextlib
|
||||
import ctypes
|
||||
import datetime
|
||||
@ -30,6 +31,7 @@ import ssl
|
||||
import subprocess
|
||||
import sys
|
||||
import tempfile
|
||||
import time
|
||||
import traceback
|
||||
import xml.etree.ElementTree
|
||||
import zlib
|
||||
@ -2735,14 +2737,66 @@ class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar):
|
||||
1. https://curl.haxx.se/docs/http-cookies.html
|
||||
"""
|
||||
_HTTPONLY_PREFIX = '#HttpOnly_'
|
||||
_ENTRY_LEN = 7
|
||||
_HEADER = '''# Netscape HTTP Cookie File
|
||||
# This file is generated by youtube-dl. Do not edit.
|
||||
|
||||
'''
|
||||
_CookieFileEntry = collections.namedtuple(
|
||||
'CookieFileEntry',
|
||||
('domain_name', 'include_subdomains', 'path', 'https_only', 'expires_at', 'name', 'value'))
|
||||
|
||||
def save(self, filename=None, ignore_discard=False, ignore_expires=False):
|
||||
"""
|
||||
Save cookies to a file.
|
||||
|
||||
Most of the code is taken from CPython 3.8 and slightly adapted
|
||||
to support cookie files with UTF-8 in both python 2 and 3.
|
||||
"""
|
||||
if filename is None:
|
||||
if self.filename is not None:
|
||||
filename = self.filename
|
||||
else:
|
||||
raise ValueError(compat_cookiejar.MISSING_FILENAME_TEXT)
|
||||
|
||||
# Store session cookies with `expires` set to 0 instead of an empty
|
||||
# string
|
||||
for cookie in self:
|
||||
if cookie.expires is None:
|
||||
cookie.expires = 0
|
||||
compat_cookiejar.MozillaCookieJar.save(self, filename, ignore_discard, ignore_expires)
|
||||
|
||||
with io.open(filename, 'w', encoding='utf-8') as f:
|
||||
f.write(self._HEADER)
|
||||
now = time.time()
|
||||
for cookie in self:
|
||||
if not ignore_discard and cookie.discard:
|
||||
continue
|
||||
if not ignore_expires and cookie.is_expired(now):
|
||||
continue
|
||||
if cookie.secure:
|
||||
secure = 'TRUE'
|
||||
else:
|
||||
secure = 'FALSE'
|
||||
if cookie.domain.startswith('.'):
|
||||
initial_dot = 'TRUE'
|
||||
else:
|
||||
initial_dot = 'FALSE'
|
||||
if cookie.expires is not None:
|
||||
expires = compat_str(cookie.expires)
|
||||
else:
|
||||
expires = ''
|
||||
if cookie.value is None:
|
||||
# cookies.txt regards 'Set-Cookie: foo' as a cookie
|
||||
# with no name, whereas http.cookiejar regards it as a
|
||||
# cookie with no value.
|
||||
name = ''
|
||||
value = cookie.name
|
||||
else:
|
||||
name = cookie.name
|
||||
value = cookie.value
|
||||
f.write(
|
||||
'\t'.join([cookie.domain, initial_dot, cookie.path,
|
||||
secure, expires, name, value]) + '\n')
|
||||
|
||||
def load(self, filename=None, ignore_discard=False, ignore_expires=False):
|
||||
"""Load cookies from a file."""
|
||||
@ -2752,12 +2806,30 @@ class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar):
|
||||
else:
|
||||
raise ValueError(compat_cookiejar.MISSING_FILENAME_TEXT)
|
||||
|
||||
def prepare_line(line):
|
||||
if line.startswith(self._HTTPONLY_PREFIX):
|
||||
line = line[len(self._HTTPONLY_PREFIX):]
|
||||
# comments and empty lines are fine
|
||||
if line.startswith('#') or not line.strip():
|
||||
return line
|
||||
cookie_list = line.split('\t')
|
||||
if len(cookie_list) != self._ENTRY_LEN:
|
||||
raise compat_cookiejar.LoadError('invalid length %d' % len(cookie_list))
|
||||
cookie = self._CookieFileEntry(*cookie_list)
|
||||
if cookie.expires_at and not cookie.expires_at.isdigit():
|
||||
raise compat_cookiejar.LoadError('invalid expires at %s' % cookie.expires_at)
|
||||
return line
|
||||
|
||||
cf = io.StringIO()
|
||||
with open(filename) as f:
|
||||
with io.open(filename, encoding='utf-8') as f:
|
||||
for line in f:
|
||||
if line.startswith(self._HTTPONLY_PREFIX):
|
||||
line = line[len(self._HTTPONLY_PREFIX):]
|
||||
cf.write(compat_str(line))
|
||||
try:
|
||||
cf.write(prepare_line(line))
|
||||
except compat_cookiejar.LoadError as e:
|
||||
write_string(
|
||||
'WARNING: skipping cookie file entry due to %s: %r\n'
|
||||
% (e, line), sys.stderr)
|
||||
continue
|
||||
cf.seek(0)
|
||||
self._really_load(cf, filename, ignore_discard, ignore_expires)
|
||||
# Session cookies are denoted by either `expires` field set to
|
||||
|
Loading…
x
Reference in New Issue
Block a user