X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fgeneric.py;h=737141f954b4acf9fcacc9e4f946983f757888ca;hb=a074e922967fa571d4f1abb1773c711747060f00;hp=875e1bf05ff274a41f46518c48e990954b7e12e5;hpb=543ec2136b2c461b339bc9dcd50ab706cdffb907;p=youtube-dl
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 875e1bf05..737141f95 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -9,6 +9,8 @@ from .common import InfoExtractor
from .youtube import YoutubeIE
from ..compat import (
compat_urllib_parse,
+ compat_urllib_parse_unquote,
+ compat_urllib_request,
compat_urlparse,
compat_xml_parse_error,
)
@@ -26,12 +28,19 @@ from ..utils import (
unsmuggle_url,
UnsupportedError,
url_basename,
+ xpath_text,
)
from .brightcove import BrightcoveIE
+from .nbc import NBCSportsVPlayerIE
from .ooyala import OoyalaIE
from .rutv import RUTVIE
+from .sportbox import SportBoxEmbedIE
from .smotri import SmotriIE
from .condenast import CondeNastIE
+from .udn import UDNEmbedIE
+from .senateisvp import SenateISVPIE
+from .bliptv import BlipTVIE
+from .svt import SVTIE
class GenericIE(InfoExtractor):
@@ -129,6 +138,20 @@ class GenericIE(InfoExtractor):
'upload_date': '20100513',
}
},
+ # Direct link to a media delivered compressed (requires Accept-Encoding == *)
+ {
+ 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
+ 'md5': '128c42e68b13950268b648275386fc74',
+ 'info_dict': {
+ 'id': 'FictionJunction-Parallel_Hearts',
+ 'ext': 'flac',
+ 'title': 'FictionJunction-Parallel_Hearts',
+ 'upload_date': '20140522',
+ },
+ 'expected_warnings': [
+ 'URL could be a direct video link, returning it as such.'
+ ]
+ },
# ooyala video
{
'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
@@ -218,6 +241,37 @@ class GenericIE(InfoExtractor):
'skip_download': True,
},
},
+ # SportBox embed
+ {
+ 'url': 'http://www.vestifinance.ru/articles/25753',
+ 'info_dict': {
+ 'id': '25753',
+ 'title': 'ÐеÑÑи Ðкономика â ÐÑÑмÑе ÑÑанÑлÑÑии Ñ Ð¤Ð¾ÑÑма-вÑÑÑавки "ÐоÑзаказ-2013"',
+ },
+ 'playlist': [{
+ 'info_dict': {
+ 'id': '370908',
+ 'title': 'ÐоÑзаказ. ÐÐµÐ½Ñ 3',
+ 'ext': 'mp4',
+ }
+ }, {
+ 'info_dict': {
+ 'id': '370905',
+ 'title': 'ÐоÑзаказ. ÐÐµÐ½Ñ 2',
+ 'ext': 'mp4',
+ }
+ }, {
+ 'info_dict': {
+ 'id': '370902',
+ 'title': 'ÐоÑзаказ. ÐÐµÐ½Ñ 1',
+ 'ext': 'mp4',
+ }
+ }],
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
+ },
# Embedded TED video
{
'url': 'http://en.support.wordpress.com/videos/ted-talks/',
@@ -526,6 +580,17 @@ class GenericIE(InfoExtractor):
},
'add_ie': ['Viddler'],
},
+ # Libsyn embed
+ {
+ 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
+ 'info_dict': {
+ 'id': '3377616',
+ 'ext': 'mp3',
+ 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
+ 'description': 'md5:601cb790edd05908957dae8aaa866465',
+ 'upload_date': '20150220',
+ },
+ },
# jwplayer YouTube
{
'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
@@ -557,6 +622,174 @@ class GenericIE(InfoExtractor):
'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
}
},
+ # Kaltura embed
+ {
+ 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
+ 'info_dict': {
+ 'id': '1_eergr3h1',
+ 'ext': 'mp4',
+ 'upload_date': '20150226',
+ 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
+ 'timestamp': int,
+ 'title': 'John Carlson Postgame 2/25/15',
+ },
+ },
+ # Eagle.Platform embed (generic URL)
+ {
+ 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
+ 'info_dict': {
+ 'id': '227304',
+ 'ext': 'mp4',
+ 'title': 'ÐавалÑнÑй вÑÑел на ÑвободÑ',
+ 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 87,
+ 'view_count': int,
+ 'age_limit': 0,
+ },
+ },
+ # ClipYou (Eagle.Platform) embed (custom URL)
+ {
+ 'url': 'http://muz-tv.ru/play/7129/',
+ 'info_dict': {
+ 'id': '12820',
+ 'ext': 'mp4',
+ 'title': "'O Sole Mio",
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 216,
+ 'view_count': int,
+ },
+ },
+ # Pladform embed
+ {
+ 'url': 'http://muz-tv.ru/kinozal/view/7400/',
+ 'info_dict': {
+ 'id': '100183293',
+ 'ext': 'mp4',
+ 'title': 'Ð¢Ð°Ð¹Ð½Ñ Ð¿ÐµÑевала ÐÑÑлова ⢠1 ÑеÑÐ¸Ñ 2 ÑаÑÑÑ',
+ 'description': 'ÐокÑменÑалÑнÑй ÑеÑиал-ÑаÑÑледование одной из ÑамÑÑ
жÑÑкиÑ
Ñайн ХХ века',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 694,
+ 'age_limit': 0,
+ },
+ },
+ # Playwire embed
+ {
+ 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
+ 'info_dict': {
+ 'id': '3519514',
+ 'ext': 'mp4',
+ 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
+ 'thumbnail': 're:^https?://.*\.png$',
+ 'duration': 45.115,
+ },
+ },
+ # 5min embed
+ {
+ 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
+ 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
+ 'info_dict': {
+ 'id': '518726732',
+ 'ext': 'mp4',
+ 'title': 'Facebook Creates "On This Day" | Crunch Report',
+ },
+ },
+ # SVT embed
+ {
+ 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
+ 'info_dict': {
+ 'id': '2900353',
+ 'ext': 'flv',
+ 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
+ 'duration': 27,
+ 'age_limit': 0,
+ },
+ },
+ # RSS feed with enclosure
+ {
+ 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
+ 'info_dict': {
+ 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
+ 'ext': 'm4v',
+ 'upload_date': '20150228',
+ 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
+ }
+ },
+ # Crooks and Liars embed
+ {
+ 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
+ 'info_dict': {
+ 'id': '8RUoRhRi',
+ 'ext': 'mp4',
+ 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
+ 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
+ 'timestamp': 1428207000,
+ 'upload_date': '20150405',
+ 'uploader': 'Heather',
+ },
+ },
+ # Crooks and Liars external embed
+ {
+ 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
+ 'info_dict': {
+ 'id': 'MTE3MjUtMzQ2MzA',
+ 'ext': 'mp4',
+ 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
+ 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
+ 'timestamp': 1265032391,
+ 'upload_date': '20100201',
+ 'uploader': 'Heather',
+ },
+ },
+ # NBC Sports vplayer embed
+ {
+ 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
+ 'info_dict': {
+ 'id': 'ln7x1qSThw4k',
+ 'ext': 'flv',
+ 'title': "PFT Live: New leader in the 'new-look' defense",
+ 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
+ },
+ },
+ # UDN embed
+ {
+ 'url': 'http://www.udn.com/news/story/7314/822787',
+ 'md5': 'fd2060e988c326991037b9aff9df21a6',
+ 'info_dict': {
+ 'id': '300346',
+ 'ext': 'mp4',
+ 'title': 'ä¸ä¸ä¸ç·å¸«è®æ§ å
¨æ ¡å¸«çåæº',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ }
+ },
+ # Ooyala embed
+ {
+ 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
+ 'info_dict': {
+ 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
+ 'ext': 'mp4',
+ 'description': 'VIDEO: Index/Match versus VLOOKUP.',
+ 'title': 'This is what separates the Excel masters from the wannabes',
+ },
+ 'params': {
+ # m3u8 downloads
+ 'skip_download': True,
+ }
+ },
+ # Contains a SMIL manifest
+ {
+ 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
+ 'info_dict': {
+ 'id': 'file',
+ 'ext': 'flv',
+ 'title': '+ Football: Lottery Champions League Europe',
+ 'uploader': 'www.telewebion.com',
+ },
+ 'params': {
+ # rtmpe downloads
+ 'skip_download': True,
+ }
+ }
]
def report_following_redirect(self, new_url):
@@ -568,11 +801,24 @@ class GenericIE(InfoExtractor):
playlist_desc_el = doc.find('./channel/description')
playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
- entries = [{
- '_type': 'url',
- 'url': e.find('link').text,
- 'title': e.find('title').text,
- } for e in doc.findall('./channel/item')]
+ entries = []
+ for it in doc.findall('./channel/item'):
+ next_url = xpath_text(it, 'link', fatal=False)
+ if not next_url:
+ enclosure_nodes = it.findall('./enclosure')
+ for e in enclosure_nodes:
+ next_url = e.attrib.get('url')
+ if next_url:
+ break
+
+ if not next_url:
+ continue
+
+ entries.append({
+ '_type': 'url',
+ 'url': next_url,
+ 'title': it.find('title').text,
+ })
return {
'_type': 'playlist',
@@ -664,7 +910,7 @@ class GenericIE(InfoExtractor):
force_videoid = smuggled_data['force_videoid']
video_id = force_videoid
else:
- video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0]
+ video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
self.to_screen('%s: Requesting header' % video_id)
@@ -686,7 +932,9 @@ class GenericIE(InfoExtractor):
full_response = None
if head_response is False:
- full_response = self._request_webpage(url, video_id)
+ request = compat_urllib_request.Request(url)
+ request.add_header('Accept-Encoding', '*')
+ full_response = self._request_webpage(request, video_id)
head_response = full_response
# Check for direct link to a video
@@ -697,7 +945,7 @@ class GenericIE(InfoExtractor):
head_response.headers.get('Last-Modified'))
return {
'id': video_id,
- 'title': os.path.splitext(url_basename(url))[0],
+ 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
'direct': True,
'formats': [{
'format_id': m.group('format_id'),
@@ -711,7 +959,17 @@ class GenericIE(InfoExtractor):
self._downloader.report_warning('Falling back on generic information extractor.')
if not full_response:
- full_response = self._request_webpage(url, video_id)
+ request = compat_urllib_request.Request(url)
+ # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
+ # making it impossible to download only chunk of the file (yet we need only 512kB to
+ # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
+ # that will always result in downloading the whole file that is not desirable.
+ # Therefore for extraction pass we have to override Accept-Encoding to any in order
+ # to accept raw bytes and being able to download only a chunk.
+ # It may probably better to solve this by checking Content-Type for application/octet-stream
+ # after HEAD request finishes, but not sure if we can rely on this.
+ request.add_header('Accept-Encoding', '*')
+ full_response = self._request_webpage(request, video_id)
# Maybe it's a direct link to a video?
# Be careful not to download the whole thing!
@@ -723,7 +981,7 @@ class GenericIE(InfoExtractor):
head_response.headers.get('Last-Modified'))
return {
'id': video_id,
- 'title': os.path.splitext(url_basename(url))[0],
+ 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
'direct': True,
'url': url,
'upload_date': upload_date,
@@ -888,12 +1146,14 @@ class GenericIE(InfoExtractor):
}
# Look for embedded blip.tv player
- mobj = re.search(r']*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)
- if mobj:
- return self.url_result('http://blip.tv/a/a-' + mobj.group(1), 'BlipTV')
- mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage)
- if mobj:
- return self.url_result(mobj.group(1), 'BlipTV')
+ bliptv_url = BlipTVIE._extract_url(webpage)
+ if bliptv_url:
+ return self.url_result(bliptv_url, 'BlipTV')
+
+ # Look for SVT player
+ svt_url = SVTIE._extract_url(webpage)
+ if svt_url:
+ return self.url_result(svt_url, 'SVT')
# Look for embedded condenast player
matches = re.findall(
@@ -931,10 +1191,24 @@ class GenericIE(InfoExtractor):
if mobj is not None:
return self.url_result(mobj.group('url'))
+ # Look for NYTimes player
+ mobj = re.search(
+ r'