aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/generic.py
diff options
context:
space:
mode:
authorremitamine <remitamine@gmail.com>2015-12-03 20:33:22 +0100
committerremitamine <remitamine@gmail.com>2015-12-03 20:33:22 +0100
commit78653a33aa00ba5205940c2baac5d9f019795b88 (patch)
tree246fd038effd402bc66de4c8afb36e6c318efcaa /youtube_dl/extractor/generic.py
parent77302fe5c989b9cafcb675c0a03642b80fa557ff (diff)
parent24dc1ed715239f85eb3d5f71a707da1dd2bc7773 (diff)
Merge remote-tracking branch 'upstream/master' into bliptv
Diffstat (limited to 'youtube_dl/extractor/generic.py')
-rw-r--r--youtube_dl/extractor/generic.py109
1 files changed, 79 insertions, 30 deletions
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 285c0ff66..4d38b0c9d 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -9,8 +9,8 @@ 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,
compat_xml_parse_error,
)
@@ -21,7 +21,7 @@ from ..utils import (
HEADRequest,
is_html,
orderedSet,
- parse_xml,
+ sanitized_Request,
smuggle_url,
unescapeHTML,
unified_strdate,
@@ -30,7 +30,10 @@ from ..utils import (
url_basename,
xpath_text,
)
-from .brightcove import BrightcoveIE
+from .brightcove import (
+ BrightcoveLegacyIE,
+ BrightcoveNewIE,
+)
from .nbc import NBCSportsVPlayerIE
from .ooyala import OoyalaIE
from .rutv import RUTVIE
@@ -140,6 +143,7 @@ class GenericIE(InfoExtractor):
'ext': 'mp4',
'title': 'Automatics, robotics and biocybernetics',
'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
+ 'upload_date': '20130627',
'formats': 'mincount:16',
'subtitles': 'mincount:1',
},
@@ -273,7 +277,7 @@ class GenericIE(InfoExtractor):
# it also tests brightcove videos that need to set the 'Referer' in the
# http requests
{
- 'add_ie': ['Brightcove'],
+ 'add_ie': ['BrightcoveLegacy'],
'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
'info_dict': {
'id': '2765128793001',
@@ -297,7 +301,7 @@ class GenericIE(InfoExtractor):
'uploader': 'thestar.com',
'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
},
- 'add_ie': ['Brightcove'],
+ 'add_ie': ['BrightcoveLegacy'],
},
{
'url': 'http://www.championat.com/video/football/v/87/87499.html',
@@ -312,7 +316,7 @@ class GenericIE(InfoExtractor):
},
{
# https://github.com/rg3/youtube-dl/issues/3541
- 'add_ie': ['Brightcove'],
+ 'add_ie': ['BrightcoveLegacy'],
'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
'info_dict': {
'id': '3866516442001',
@@ -818,6 +822,19 @@ class GenericIE(InfoExtractor):
'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
},
},
+ # Kaltura embed protected with referrer
+ {
+ 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
+ 'info_dict': {
+ 'id': '1_g4fbemnq',
+ 'ext': 'mp4',
+ 'title': 'Violetta - Achter De Schermen - Ruggero',
+ 'description': 'Achter de schermen met Ruggero',
+ 'timestamp': 1435133761,
+ 'upload_date': '20150624',
+ 'uploader_id': 'echojecka',
+ },
+ },
# Eagle.Platform embed (generic URL)
{
'url': 'http://lenta.ru/news/2015/03/06/navalny/',
@@ -1029,6 +1046,31 @@ class GenericIE(InfoExtractor):
'ext': 'mp4',
'title': 'cinemasnob',
},
+ },
+ # BrightcoveInPageEmbed embed
+ {
+ 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
+ 'info_dict': {
+ 'id': '4238694884001',
+ 'ext': 'flv',
+ 'title': 'Tabletop: Dread, Last Thoughts',
+ 'description': 'Tabletop: Dread, Last Thoughts',
+ 'duration': 51690,
+ },
+ },
+ # JWPlayer with M3U8
+ {
+ 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
+ 'info_dict': {
+ 'id': 'playlist',
+ 'ext': 'mp4',
+ 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
+ 'uploader': 'ren.tv',
+ },
+ 'params': {
+ # m3u8 downloads
+ 'skip_download': True,
+ }
}
]
@@ -1172,7 +1214,7 @@ class GenericIE(InfoExtractor):
full_response = None
if head_response is False:
- request = compat_urllib_request.Request(url)
+ request = sanitized_Request(url)
request.add_header('Accept-Encoding', '*')
full_response = self._request_webpage(request, video_id)
head_response = full_response
@@ -1201,7 +1243,7 @@ class GenericIE(InfoExtractor):
'%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
if not full_response:
- request = compat_urllib_request.Request(url)
+ request = sanitized_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
@@ -1236,7 +1278,7 @@ 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):
@@ -1288,14 +1330,14 @@ class GenericIE(InfoExtractor):
return self.playlist_result(
urlrs, playlist_id=video_id, playlist_title=video_title)
- # Look for BrightCove:
- bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
+ # Look for Brightcove Legacy Studio embeds
+ bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
if bc_urls:
self.to_screen('Brightcove video detected.')
entries = [{
'_type': 'url',
'url': smuggle_url(bc_url, {'Referer': url}),
- 'ie_key': 'Brightcove'
+ 'ie_key': 'BrightcoveLegacy'
} for bc_url in bc_urls]
return {
@@ -1305,6 +1347,11 @@ class GenericIE(InfoExtractor):
'entries': entries,
}
+ # Look for Brightcove New Studio embeds
+ bc_urls = BrightcoveNewIE._extract_urls(webpage)
+ if bc_urls:
+ return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
+
# Look for embedded rtl.nl player
matches = re.findall(
r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
@@ -1665,10 +1712,12 @@ class GenericIE(InfoExtractor):
return self.url_result(mobj.group('url'), 'Zapiks')
# Look for Kaltura embeds
- mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
- re.search(r'(?s)(["\'])(?:https?:)?//cdnapisec\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?\1.*?entry_id\s*:\s*(["\'])(?P<id>[^\2]+?)\2', webpage))
+ mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
+ re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage))
if mobj is not None:
- return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
+ return self.url_result(smuggle_url(
+ 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
+ {'source_url': url}), 'Kaltura')
# Look for Eagle.Platform embeds
mobj = re.search(
@@ -1713,7 +1762,7 @@ class GenericIE(InfoExtractor):
# Look for UDN embeds
mobj = re.search(
- r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
+ r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
if mobj is not None:
return self.url_result(
compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
@@ -1833,6 +1882,7 @@ class GenericIE(InfoExtractor):
entries = []
for video_url in found:
+ video_url = video_url.replace('\\/', '/')
video_url = compat_urlparse.urljoin(url, video_url)
video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
@@ -1844,25 +1894,24 @@ class GenericIE(InfoExtractor):
# here's a fun little line of code for you:
video_id = os.path.splitext(video_id)[0]
+ entry_info_dict = {
+ 'id': video_id,
+ 'uploader': video_uploader,
+ 'title': video_title,
+ 'age_limit': age_limit,
+ }
+
ext = determine_ext(video_url)
if ext == 'smil':
- entries.append({
- 'id': video_id,
- 'formats': self._extract_smil_formats(video_url, video_id),
- 'uploader': video_uploader,
- 'title': video_title,
- 'age_limit': age_limit,
- })
+ entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
elif ext == 'xspf':
return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
+ elif ext == 'm3u8':
+ entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
else:
- entries.append({
- 'id': video_id,
- 'url': video_url,
- 'uploader': video_uploader,
- 'title': video_title,
- 'age_limit': age_limit,
- })
+ entry_info_dict['url'] = video_url
+
+ entries.append(entry_info_dict)
if len(entries) == 1:
return entries[0]