mirror of
https://github.com/l1ving/youtube-dl
synced 2025-03-13 16:49:58 +08:00
Merge branch 'track-upstream-master'
This commit is contained in:
Your Name
commit
b41f8ed971
@ -126,6 +126,7 @@ from .helsinki import HelsinkiIE
|
||||
from .hentaistigma import HentaiStigmaIE
|
||||
from .hotnewhiphop import HotNewHipHopIE
|
||||
from .howcast import HowcastIE
|
||||
from .howstuffworks import HowStuffWorksIE
|
||||
from .huffpost import HuffPostIE
|
||||
from .hypem import HypemIE
|
||||
from .iconosquare import IconosquareIE
|
||||
|
||||
@ -30,7 +30,7 @@ class DFBIE(InfoExtractor):
|
||||
video_id)
|
||||
video_info = player_info.find('video')
|
||||
|
||||
f4m_info = self._download_xml(video_info.find('url').text, video_id)
|
||||
f4m_info = self._download_xml(self._proto_relative_url(video_info.find('url').text.strip()), video_id)
|
||||
token_el = f4m_info.find('token')
|
||||
manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + '&hdcore=3.2.0'
|
||||
|
||||
|
||||
@ -706,6 +706,13 @@ class GenericIE(InfoExtractor):
|
||||
url = unescapeHTML(mobj.group('url'))
|
||||
return self.url_result(url, ie='MTVServicesEmbedded')
|
||||
|
||||
# Look for embedded yahoo player
|
||||
mobj = re.search(
|
||||
r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
|
||||
webpage)
|
||||
if mobj is not None:
|
||||
return self.url_result(mobj.group('url'), 'Yahoo')
|
||||
|
||||
# Start with something easy: JW Player in SWFObject
|
||||
found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
|
||||
if not found:
|
||||
|
||||
134
youtube_dl/extractor/howstuffworks.py
Normal file
134
youtube_dl/extractor/howstuffworks.py
Normal file
@ -0,0 +1,134 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import json
|
||||
import random
|
||||
import string
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import find_xpath_attr
|
||||
|
||||
|
||||
class HowStuffWorksIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://[\da-z-]+\.howstuffworks\.com/(?:[^/]+/)*\d+-(?P<id>.+?)-video\.htm'
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm',
|
||||
'info_dict': {
|
||||
'id': '450221',
|
||||
'display_id': 'cool-jobs-iditarod-musher',
|
||||
'ext': 'flv',
|
||||
'title': 'Cool Jobs - Iditarod Musher',
|
||||
'description': 'md5:82bb58438a88027b8186a1fccb365f90',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
},
|
||||
'params': {
|
||||
# md5 is not consistent
|
||||
'skip_download': True
|
||||
}
|
||||
},
|
||||
{
|
||||
'url': 'http://adventure.howstuffworks.com/39516-deadliest-catch-jakes-farewell-pots-video.htm',
|
||||
'info_dict': {
|
||||
'id': '553470',
|
||||
'display_id': 'deadliest-catch-jakes-farewell-pots',
|
||||
'ext': 'mp4',
|
||||
'title': 'Deadliest Catch: Jake\'s Farewell Pots',
|
||||
'description': 'md5:9632c346d5e43ee238028c9cefd8dbbc',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
},
|
||||
'params': {
|
||||
# md5 is not consistent
|
||||
'skip_download': True
|
||||
}
|
||||
},
|
||||
{
|
||||
'url': 'http://entertainment.howstuffworks.com/arts/2706-sword-swallowing-1-by-dan-meyer-video.htm',
|
||||
'info_dict': {
|
||||
'id': '440011',
|
||||
'display_id': 'sword-swallowing-1-by-dan-meyer',
|
||||
'ext': 'flv',
|
||||
'title': 'Sword Swallowing #1 by Dan Meyer',
|
||||
'description': 'md5:b2409e88172913e2e7d3d1159b0ef735',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
},
|
||||
'params': {
|
||||
# md5 is not consistent
|
||||
'skip_download': True
|
||||
}
|
||||
},
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
display_id = mobj.group('id')
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
content_id = self._search_regex(r'var siteSectionId="(\d+)";', webpage, 'content id')
|
||||
|
||||
mp4 = self._search_regex(
|
||||
r'''(?xs)var\s+clip\s*=\s*{\s*
|
||||
.+?\s*
|
||||
content_id\s*:\s*%s\s*,\s*
|
||||
.+?\s*
|
||||
mp4\s*:\s*\[(.*?),?\]\s*
|
||||
};\s*
|
||||
videoData\.push\(clip\);''' % content_id,
|
||||
webpage, 'mp4', fatal=False, default=None)
|
||||
|
||||
smil = self._download_xml(
|
||||
'http://services.media.howstuffworks.com/videos/%s/smil-service.smil' % content_id,
|
||||
content_id, 'Downloading video SMIL')
|
||||
|
||||
http_base = find_xpath_attr(
|
||||
smil,
|
||||
'./{0}head/{0}meta'.format('{http://www.w3.org/2001/SMIL20/Language}'),
|
||||
'name',
|
||||
'httpBase').get('content')
|
||||
|
||||
def random_string(str_len=0):
|
||||
return ''.join([random.choice(string.ascii_uppercase) for _ in range(str_len)])
|
||||
|
||||
URL_SUFFIX = '?v=2.11.3&fp=LNX 11,2,202,356&r=%s&g=%s' % (random_string(5), random_string(12))
|
||||
|
||||
formats = []
|
||||
|
||||
if mp4:
|
||||
for video in json.loads('[%s]' % mp4):
|
||||
bitrate = video['bitrate']
|
||||
fmt = {
|
||||
'url': video['src'].replace('http://pmd.video.howstuffworks.com', http_base) + URL_SUFFIX,
|
||||
'format_id': bitrate,
|
||||
}
|
||||
m = re.search(r'(?P<vbr>\d+)[Kk]', bitrate)
|
||||
if m:
|
||||
fmt['vbr'] = int(m.group('vbr'))
|
||||
formats.append(fmt)
|
||||
else:
|
||||
for video in smil.findall(
|
||||
'.//{0}body/{0}switch/{0}video'.format('{http://www.w3.org/2001/SMIL20/Language}')):
|
||||
vbr = int(video.attrib['system-bitrate']) / 1000
|
||||
formats.append({
|
||||
'url': '%s/%s%s' % (http_base, video.attrib['src'], URL_SUFFIX),
|
||||
'format_id': '%dk' % vbr,
|
||||
'vbr': vbr,
|
||||
})
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
title = self._og_search_title(webpage)
|
||||
TITLE_SUFFIX = ' : HowStuffWorks'
|
||||
if title.endswith(TITLE_SUFFIX):
|
||||
title = title[:-len(TITLE_SUFFIX)]
|
||||
|
||||
description = self._og_search_description(webpage)
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
|
||||
return {
|
||||
'id': content_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'formats': formats,
|
||||
}
|
||||
@ -15,7 +15,7 @@ from ..utils import (
|
||||
|
||||
class YahooIE(InfoExtractor):
|
||||
IE_DESC = 'Yahoo screen and movies'
|
||||
_VALID_URL = r'https?://(?:screen|movies)\.yahoo\.com/.*?-(?P<id>[0-9]+)(?:-[a-z]+)?\.html'
|
||||
_VALID_URL = r'(?P<url>https?://(?:screen|movies)\.yahoo\.com/.*?-(?P<id>[0-9]+)(?:-[a-z]+)?\.html)'
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
|
||||
@ -46,12 +46,23 @@ class YahooIE(InfoExtractor):
|
||||
'title': 'The World Loves Spider-Man',
|
||||
'description': '''People all over the world are celebrating the release of \"The Amazing Spider-Man 2.\" We're taking a look at the enthusiastic response Spider-Man has received from viewers all over the world.''',
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
'url': 'https://screen.yahoo.com/community/community-sizzle-reel-203225340.html?format=embed',
|
||||
'md5': '60e8ac193d8fb71997caa8fce54c6460',
|
||||
'info_dict': {
|
||||
'id': '4fe78544-8d48-39d8-97cd-13f205d9fcdb',
|
||||
'ext': 'mp4',
|
||||
'title': "Yahoo Saves 'Community'",
|
||||
'description': 'md5:4d4145af2fd3de00cbb6c1d664105053',
|
||||
}
|
||||
},
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
url = mobj.group('url')
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
items_json = self._search_regex(
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user