aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/__init__.py12
-rw-r--r--youtube_dl/extractor/bliptv.py75
-rw-r--r--youtube_dl/extractor/cmt.py19
-rw-r--r--youtube_dl/extractor/collegehumor.py106
-rw-r--r--youtube_dl/extractor/comedycentral.py4
-rw-r--r--youtube_dl/extractor/common.py5
-rw-r--r--youtube_dl/extractor/dreisat.py6
-rw-r--r--youtube_dl/extractor/generic.py2
-rw-r--r--youtube_dl/extractor/imdb.py29
-rw-r--r--youtube_dl/extractor/jpopsukitv.py73
-rw-r--r--youtube_dl/extractor/lynda.py102
-rw-r--r--youtube_dl/extractor/macgamestore.py43
-rw-r--r--youtube_dl/extractor/mixcloud.py2
-rw-r--r--youtube_dl/extractor/mtv.py2
-rw-r--r--youtube_dl/extractor/pornhd.py2
-rw-r--r--youtube_dl/extractor/soundcloud.py4
-rw-r--r--youtube_dl/extractor/wistia.py1
-rw-r--r--youtube_dl/extractor/youtube.py1
18 files changed, 382 insertions, 106 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index a39a1e2f4..21d564dba 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -28,6 +28,7 @@ from .channel9 import Channel9IE
from .cinemassacre import CinemassacreIE
from .clipfish import ClipfishIE
from .clipsyndicate import ClipsyndicateIE
+from .cmt import CMTIE
from .cnn import CNNIE
from .collegehumor import CollegeHumorIE
from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
@@ -79,7 +80,10 @@ from .hotnewhiphop import HotNewHipHopIE
from .howcast import HowcastIE
from .hypem import HypemIE
from .ign import IGNIE, OneUPIE
-from .imdb import ImdbIE
+from .imdb import (
+ ImdbIE,
+ ImdbListIE
+)
from .ina import InaIE
from .infoq import InfoQIE
from .instagram import InstagramIE
@@ -91,12 +95,18 @@ from .ivi import (
from .jeuxvideo import JeuxVideoIE
from .jukebox import JukeboxIE
from .justintv import JustinTVIE
+from .jpopsukitv import JpopsukiIE
from .kankan import KankanIE
from .keezmovies import KeezMoviesIE
from .kickstarter import KickStarterIE
from .keek import KeekIE
from .liveleak import LiveLeakIE
from .livestream import LivestreamIE, LivestreamOriginalIE
+from .lynda import (
+ LyndaIE,
+ LyndaCourseIE
+)
+from .macgamestore import MacGameStoreIE
from .mdr import MDRIE
from .metacafe import MetacafeIE
from .metacritic import MetacriticIE
diff --git a/youtube_dl/extractor/bliptv.py b/youtube_dl/extractor/bliptv.py
index 8a8c2e7a8..4f1272f29 100644
--- a/youtube_dl/extractor/bliptv.py
+++ b/youtube_dl/extractor/bliptv.py
@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
import datetime
import json
import re
@@ -21,36 +23,35 @@ class BlipTVIE(InfoExtractor):
"""Information extractor for blip.tv"""
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv/((.+/)|(play/)|(api\.swf#))(.+)$'
- _URL_EXT = r'^.*\.([a-z0-9]+)$'
- IE_NAME = u'blip.tv'
+
_TEST = {
- u'url': u'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352',
- u'file': u'5779306.m4v',
- u'md5': u'80baf1ec5c3d2019037c1c707d676b9f',
- u'info_dict': {
- u"upload_date": u"20111205",
- u"description": u"md5:9bc31f227219cde65e47eeec8d2dc596",
- u"uploader": u"Comic Book Resources - CBR TV",
- u"title": u"CBR EXCLUSIVE: \"Gotham City Imposters\" Bats VS Jokerz Short 3"
+ 'url': 'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352',
+ 'file': '5779306.mov',
+ 'md5': 'c6934ad0b6acf2bd920720ec888eb812',
+ 'info_dict': {
+ 'upload_date': '20111205',
+ 'description': 'md5:9bc31f227219cde65e47eeec8d2dc596',
+ 'uploader': 'Comic Book Resources - CBR TV',
+ 'title': 'CBR EXCLUSIVE: "Gotham City Imposters" Bats VS Jokerz Short 3',
}
}
def report_direct_download(self, title):
"""Report information extraction."""
- self.to_screen(u'%s: Direct download detected' % title)
+ self.to_screen('%s: Direct download detected' % title)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
+ raise ExtractorError('Invalid URL: %s' % url)
# See https://github.com/rg3/youtube-dl/issues/857
embed_mobj = re.search(r'^(?:https?://)?(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)([a-zA-Z0-9]+)', url)
if embed_mobj:
info_url = 'http://blip.tv/play/%s.x?p=1' % embed_mobj.group(1)
info_page = self._download_webpage(info_url, embed_mobj.group(1))
- video_id = self._search_regex(r'data-episode-id="(\d+)', info_page, u'video_id')
- return self.url_result('http://blip.tv/a/a-'+video_id, 'BlipTV')
+ video_id = self._search_regex(r'data-episode-id="(\d+)', info_page, 'video_id')
+ return self.url_result('http://blip.tv/a/a-' + video_id, 'BlipTV')
if '?' in url:
cchar = '&'
@@ -61,13 +62,13 @@ class BlipTVIE(InfoExtractor):
request.add_header('User-Agent', 'iTunes/10.6.1')
self.report_extraction(mobj.group(1))
urlh = self._request_webpage(request, None, False,
- u'unable to download video info webpage')
+ 'unable to download video info webpage')
try:
json_code_bytes = urlh.read()
json_code = json_code_bytes.decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- raise ExtractorError(u'Unable to read video info webpage: %s' % compat_str(err))
+ raise ExtractorError('Unable to read video info webpage: %s' % compat_str(err))
try:
json_data = json.loads(json_code)
@@ -77,32 +78,38 @@ class BlipTVIE(InfoExtractor):
data = json_data
upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
+ formats = []
if 'additionalMedia' in data:
- formats = sorted(data['additionalMedia'], key=lambda f: int(f['media_height']))
- best_format = formats[-1]
- video_url = best_format['url']
+ for f in sorted(data['additionalMedia'], key=lambda f: int(f['media_height'])):
+ if not int(f['media_width']): # filter m3u8
+ continue
+ formats.append({
+ 'url': f['url'],
+ 'format_id': f['role'],
+ 'width': int(f['media_width']),
+ 'height': int(f['media_height']),
+ })
else:
- video_url = data['media']['url']
- umobj = re.match(self._URL_EXT, video_url)
- if umobj is None:
- raise ValueError('Can not determine filename extension')
- ext = umobj.group(1)
+ formats.append({
+ 'url': data['media']['url'],
+ 'width': int(data['media']['width']),
+ 'height': int(data['media']['height']),
+ })
+
+ self._sort_formats(formats)
return {
'id': compat_str(data['item_id']),
- 'url': video_url,
'uploader': data['display_name'],
'upload_date': upload_date,
'title': data['title'],
- 'ext': ext,
- 'format': data['media']['mimeType'],
'thumbnail': data['thumbnailUrl'],
'description': data['description'],
- 'player_url': data['embedUrl'],
'user_agent': 'iTunes/10.6.1',
+ 'formats': formats,
}
except (ValueError, KeyError) as err:
- raise ExtractorError(u'Unable to parse video information: %s' % repr(err))
+ raise ExtractorError('Unable to parse video information: %s' % repr(err))
class BlipTVUserIE(InfoExtractor):
@@ -110,19 +117,19 @@ class BlipTVUserIE(InfoExtractor):
_VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$'
_PAGE_SIZE = 12
- IE_NAME = u'blip.tv:user'
+ IE_NAME = 'blip.tv:user'
def _real_extract(self, url):
# Extract username
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
+ raise ExtractorError('Invalid URL: %s' % url)
username = mobj.group(1)
page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1'
- page = self._download_webpage(url, username, u'Downloading user page')
+ page = self._download_webpage(url, username, 'Downloading user page')
mobj = re.search(r'data-users-id="([^"]+)"', page)
page_base = page_base % mobj.group(1)
@@ -138,7 +145,7 @@ class BlipTVUserIE(InfoExtractor):
while True:
url = page_base + "&page=" + str(pagenum)
page = self._download_webpage(url, username,
- u'Downloading video ids from page %d' % pagenum)
+ 'Downloading video ids from page %d' % pagenum)
# Extract video identifiers
ids_in_page = []
@@ -160,6 +167,6 @@ class BlipTVUserIE(InfoExtractor):
pagenum += 1
- urls = [u'http://blip.tv/%s' % video_id for video_id in video_ids]
+ urls = ['http://blip.tv/%s' % video_id for video_id in video_ids]
url_entries = [self.url_result(vurl, 'BlipTV') for vurl in urls]
return [self.playlist_result(url_entries, playlist_title = username)]
diff --git a/youtube_dl/extractor/cmt.py b/youtube_dl/extractor/cmt.py
new file mode 100644
index 000000000..88e0e9aba
--- /dev/null
+++ b/youtube_dl/extractor/cmt.py
@@ -0,0 +1,19 @@
+from .mtv import MTVIE
+
+class CMTIE(MTVIE):
+ IE_NAME = u'cmt.com'
+ _VALID_URL = r'https?://www\.cmt\.com/videos/.+?/(?P<videoid>[^/]+)\.jhtml'
+ _FEED_URL = 'http://www.cmt.com/sitewide/apps/player/embed/rss/'
+
+ _TESTS = [
+ {
+ u'url': u'http://www.cmt.com/videos/garth-brooks/989124/the-call-featuring-trisha-yearwood.jhtml#artist=30061',
+ u'md5': u'e6b7ef3c4c45bbfae88061799bbba6c2',
+ u'info_dict': {
+ u'id': u'989124',
+ u'ext': u'mp4',
+ u'title': u'Garth Brooks - "The Call (featuring Trisha Yearwood)"',
+ u'description': u'Blame It All On My Roots',
+ },
+ },
+ ]
diff --git a/youtube_dl/extractor/collegehumor.py b/youtube_dl/extractor/collegehumor.py
index b27c1dfc5..d10b7bd0c 100644
--- a/youtube_dl/extractor/collegehumor.py
+++ b/youtube_dl/extractor/collegehumor.py
@@ -1,82 +1,68 @@
+from __future__ import unicode_literals
+
+import json
import re
from .common import InfoExtractor
-from ..utils import (
- compat_urllib_parse_urlparse,
- determine_ext,
-
- ExtractorError,
-)
class CollegeHumorIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/?(?P<shorttitle>.*)$'
_TESTS = [{
- u'url': u'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
- u'file': u'6902724.mp4',
- u'md5': u'1264c12ad95dca142a9f0bf7968105a0',
- u'info_dict': {
- u'title': u'Comic-Con Cosplay Catastrophe',
- u'description': u'Fans get creative this year at San Diego. Too creative. And yes, that\'s really Joss Whedon.',
+ 'url': 'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
+ 'file': '6902724.mp4',
+ 'md5': 'dcc0f5c1c8be98dc33889a191f4c26bd',
+ 'info_dict': {
+ 'title': 'Comic-Con Cosplay Catastrophe',
+ 'description': 'Fans get creative this year at San Diego. Too',
+ 'age_limit': 13,
},
},
{
- u'url': u'http://www.collegehumor.com/video/3505939/font-conference',
- u'file': u'3505939.mp4',
- u'md5': u'c51ca16b82bb456a4397987791a835f5',
- u'info_dict': {
- u'title': u'Font Conference',
- u'description': u'This video wasn\'t long enough, so we made it double-spaced.',
+ 'url': 'http://www.collegehumor.com/video/3505939/font-conference',
+ 'file': '3505939.mp4',
+ 'md5': '72fa701d8ef38664a4dbb9e2ab721816',
+ 'info_dict': {
+ 'title': 'Font Conference',
+ 'description': 'This video wasn\'t long enough, so we made it double-spaced.',
+ 'age_limit': 10,
},
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('videoid')
- info = {
- 'id': video_id,
- 'uploader': None,
- 'upload_date': None,
- }
-
- self.report_extraction(video_id)
- xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id
- mdoc = self._download_xml(xmlUrl, video_id,
- u'Downloading info XML',
- u'Unable to download video info XML')
+ jsonUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id + '.json'
+ data = json.loads(self._download_webpage(
+ jsonUrl, video_id, 'Downloading info JSON'))
+ vdata = data['video']
- try:
- videoNode = mdoc.findall('./video')[0]
- youtubeIdNode = videoNode.find('./youtubeID')
- if youtubeIdNode is not None:
- return self.url_result(youtubeIdNode.text, 'Youtube')
- info['description'] = videoNode.findall('./description')[0].text
- info['title'] = videoNode.findall('./caption')[0].text
- info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
- next_url = videoNode.findall('./file')[0].text
- except IndexError:
- raise ExtractorError(u'Invalid metadata XML file')
-
- if next_url.endswith(u'manifest.f4m'):
- manifest_url = next_url + '?hdcore=2.10.3'
- adoc = self._download_xml(manifest_url, video_id,
- u'Downloading XML manifest',
- u'Unable to download video info XML')
-
- try:
- video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
- except IndexError:
- raise ExtractorError(u'Invalid manifest file')
- url_pr = compat_urllib_parse_urlparse(info['thumbnail'])
- info['url'] = url_pr.scheme + '://' + url_pr.netloc + video_id[:-2].replace('.csmil','').replace(',','')
- info['ext'] = 'mp4'
+ AGE_LIMITS = {'nc17': 18, 'r': 18, 'pg13': 13, 'pg': 10, 'g': 0}
+ rating = vdata.get('rating')
+ if rating:
+ age_limit = AGE_LIMITS.get(rating.lower())
else:
- # Old-style direct links
- info['url'] = next_url
- info['ext'] = determine_ext(info['url'])
+ age_limit = None # None = No idea
+
+ PREFS = {'high_quality': 2, 'low_quality': 0}
+ formats = []
+ for format_key in ('mp4', 'webm'):
+ for qname, qurl in vdata[format_key].items():
+ formats.append({
+ 'format_id': format_key + '_' + qname,
+ 'url': qurl,
+ 'format': format_key,
+ 'preference': PREFS.get(qname),
+ })
+ self._sort_formats(formats)
- return info
+ return {
+ 'id': video_id,
+ 'title': vdata['title'],
+ 'description': vdata.get('description'),
+ 'thumbnail': vdata.get('thumbnail'),
+ 'formats': formats,
+ 'age_limit': age_limit,
+ }
diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py
index a54ce3ee7..27bd8256e 100644
--- a/youtube_dl/extractor/comedycentral.py
+++ b/youtube_dl/extractor/comedycentral.py
@@ -12,7 +12,9 @@ from ..utils import (
class ComedyCentralIE(MTVServicesInfoExtractor):
- _VALID_URL = r'https?://(?:www.)?comedycentral.com/(video-clips|episodes|cc-studios)/(?P<title>.*)'
+ _VALID_URL = r'''(?x)https?://(?:www.)?comedycentral.com/
+ (video-clips|episodes|cc-studios|video-collections)
+ /(?P<title>.*)'''
_FEED_URL = u'http://comedycentral.com/feeds/mrss/'
_TEST = {
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index f34d36cb0..f498bcf6f 100644
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -69,7 +69,8 @@ class InfoExtractor(object):
download, lower-case.
"http", "https", "rtsp", "rtmp" or so.
* preference Order number of this format. If this field is
- present, the formats get sorted by this field.
+ present and not None, the formats get sorted
+ by this field.
-1 for default (order by other properties),
-2 or smaller for less than default.
url: Final video URL.
@@ -377,7 +378,7 @@ class InfoExtractor(object):
@staticmethod
def _og_regexes(prop):
content_re = r'content=(?:"([^>]+?)"|\'(.+?)\')'
- property_re = r'property=[\'"]og:%s[\'"]' % re.escape(prop)
+ property_re = r'(?:name|property)=[\'"]og:%s[\'"]' % re.escape(prop)
template = r'<meta[^>]+?%s[^>]+?%s'
return [
template % (property_re, content_re),
diff --git a/youtube_dl/extractor/dreisat.py b/youtube_dl/extractor/dreisat.py
index 416e25156..0b11d1f10 100644
--- a/youtube_dl/extractor/dreisat.py
+++ b/youtube_dl/extractor/dreisat.py
@@ -10,11 +10,11 @@ from ..utils import (
class DreiSatIE(InfoExtractor):
IE_NAME = '3sat'
- _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/index\.php\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
+ _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
_TEST = {
u"url": u"http://www.3sat.de/mediathek/index.php?obj=36983",
- u'file': u'36983.webm',
- u'md5': u'57c97d0469d71cf874f6815aa2b7c944',
+ u'file': u'36983.mp4',
+ u'md5': u'9dcfe344732808dbfcc901537973c922',
u'info_dict': {
u"title": u"Kaffeeland Schweiz",
u"description": u"Über 80 Kaffeeröstereien liefern in der Schweiz das Getränk, in das das Land so vernarrt ist: Mehr als 1000 Tassen trinkt ein Schweizer pro Jahr. SCHWEIZWEIT nimmt die Kaffeekultur unter die...",
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index f1b152f62..57a6b1820 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -162,6 +162,8 @@ class GenericIE(InfoExtractor):
return self.url_result('http://' + url)
video_id = os.path.splitext(url.split('/')[-1])[0]
+ self.to_screen(u'%s: Requesting header' % video_id)
+
try:
response = self._send_head(url)
diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py
index e5332cce8..16926b4d3 100644
--- a/youtube_dl/extractor/imdb.py
+++ b/youtube_dl/extractor/imdb.py
@@ -55,3 +55,32 @@ class ImdbIE(InfoExtractor):
'description': descr,
'thumbnail': format_info['slate'],
}
+
+class ImdbListIE(InfoExtractor):
+ IE_NAME = u'imdb:list'
+ IE_DESC = u'Internet Movie Database lists'
+ _VALID_URL = r'http://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ list_id = mobj.group('id')
+
+ # RSS XML is sometimes malformed
+ rss = self._download_webpage('http://rss.imdb.com/list/%s' % list_id, list_id, u'Downloading list RSS')
+ list_title = self._html_search_regex(r'<title>(.*?)</title>', rss, u'list title')
+
+ # Export is independent of actual author_id, but returns 404 if no author_id is provided.
+ # However, passing dummy author_id seems to be enough.
+ csv = self._download_webpage('http://www.imdb.com/list/export?list_id=%s&author_id=ur00000000' % list_id,
+ list_id, u'Downloading list CSV')
+
+ entries = []
+ for item in csv.split('\n')[1:]:
+ cols = item.split(',')
+ if len(cols) < 2:
+ continue
+ item_id = cols[1][1:-1]
+ if item_id.startswith('vi'):
+ entries.append(self.url_result('http://www.imdb.com/video/imdb/%s' % item_id, 'Imdb'))
+
+ return self.playlist_result(entries, list_id, list_title) \ No newline at end of file
diff --git a/youtube_dl/extractor/jpopsukitv.py b/youtube_dl/extractor/jpopsukitv.py
new file mode 100644
index 000000000..aad782578
--- /dev/null
+++ b/youtube_dl/extractor/jpopsukitv.py
@@ -0,0 +1,73 @@
+# coding=utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ int_or_none,
+ unified_strdate,
+)
+
+
+class JpopsukiIE(InfoExtractor):
+ IE_NAME = 'jpopsuki.tv'
+ _VALID_URL = r'https?://(?:www\.)?jpopsuki\.tv/video/(.*?)/(?P<id>\S+)'
+
+ _TEST = {
+ 'url': 'http://www.jpopsuki.tv/video/ayumi-hamasaki---evolution/00be659d23b0b40508169cdee4545771',
+ 'md5': '88018c0c1a9b1387940e90ec9e7e198e',
+ 'file': '00be659d23b0b40508169cdee4545771.mp4',
+ 'info_dict': {
+ 'id': '00be659d23b0b40508169cdee4545771',
+ 'title': 'ayumi hamasaki - evolution',
+ 'description': 'Release date: 2001.01.31\r\n浜崎あゆみ - evolution',
+ 'thumbnail': 'http://www.jpopsuki.tv/cache/89722c74d2a2ebe58bcac65321c115b2.jpg',
+ 'uploader': 'plama_chan',
+ 'uploader_id': '404',
+ 'upload_date': '20121101'
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, video_id)
+
+ video_url = 'http://www.jpopsuki.tv' + self._html_search_regex(
+ r'<source src="(.*?)" type', webpage, 'video url')
+
+ video_title = self._og_search_title(webpage)
+ description = self._og_search_description(webpage)
+ thumbnail = self._og_search_thumbnail(webpage)
+ uploader = self._html_search_regex(
+ r'<li>from: <a href="/user/view/user/(.*?)/uid/',
+ webpage, 'video uploader', fatal=False)
+ uploader_id = self._html_search_regex(
+ r'<li>from: <a href="/user/view/user/\S*?/uid/(\d*)',
+ webpage, 'video uploader_id', fatal=False)
+ upload_date = self._html_search_regex(
+ r'<li>uploaded: (.*?)</li>', webpage, 'video upload_date',
+ fatal=False)
+ if upload_date is not None:
+ upload_date = unified_strdate(upload_date)
+ view_count_str = self._html_search_regex(
+ r'<li>Hits: ([0-9]+?)</li>', webpage, 'video view_count',
+ fatal=False)
+ comment_count_str = self._html_search_regex(
+ r'<h2>([0-9]+?) comments</h2>', webpage, 'video comment_count',
+ fatal=False)
+
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'title': video_title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'uploader': uploader,
+ 'uploader_id': uploader_id,
+ 'upload_date': upload_date,
+ 'view_count': int_or_none(view_count_str),
+ 'comment_count': int_or_none(comment_count_str),
+ }
diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py
new file mode 100644
index 000000000..592ed747a
--- /dev/null
+++ b/youtube_dl/extractor/lynda.py
@@ -0,0 +1,102 @@
+from __future__ import unicode_literals
+
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class LyndaIE(InfoExtractor):
+ IE_NAME = 'lynda'
+ IE_DESC = 'lynda.com videos'
+ _VALID_URL = r'https?://www\.lynda\.com/[^/]+/[^/]+/\d+/(\d+)-\d\.html'
+
+ _TEST = {
+ 'url': 'http://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html',
+ 'file': '114408.mp4',
+ 'md5': 'ecfc6862da89489161fb9cd5f5a6fac1',
+ u"info_dict": {
+ 'title': 'Using the exercise files',
+ 'duration': 68
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group(1)
+
+ page = self._download_webpage('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 and video_json['Status'] == 'NotFound':
+ raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+
+ if video_json['HasAccess'] is False:
+ raise ExtractorError('Video %s is only available for members' % video_id, expected=True)
+
+ video_id = video_json['ID']
+ duration = video_json['DurationInSeconds']
+ title = video_json['Title']
+
+ formats = [{'url': fmt['Url'],
+ 'ext': fmt['Extension'],
+ 'width': fmt['Width'],
+ 'height': fmt['Height'],
+ 'filesize': fmt['FileSize'],
+ 'format_id': fmt['Resolution']
+ } for fmt in video_json['Formats']]
+
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'duration': duration,
+ 'formats': formats
+ }
+
+
+class LyndaCourseIE(InfoExtractor):
+ IE_NAME = 'lynda:course'
+ IE_DESC = 'lynda.com online courses'
+
+ # Course link equals to welcome/introduction video link of same course
+ # We will recognize it as course link
+ _VALID_URL = r'https?://(?:www|m)\.lynda\.com/(?P<coursepath>[^/]+/[^/]+/(?P<courseid>\d+))-\d\.html'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ course_path = mobj.group('coursepath')
+ course_id = mobj.group('courseid')
+
+ page = self._download_webpage('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':
+ raise ExtractorError('Course %s does not exist' % course_id, expected=True)
+
+ unaccessible_videos = 0
+ videos = []
+
+ for chapter in course_json['Chapters']:
+ for video in chapter['Videos']:
+ if video['HasAccess'] is not True:
+ unaccessible_videos += 1
+ continue
+ videos.append(video['ID'])
+
+ if unaccessible_videos > 0:
+ self._downloader.report_warning('%s videos are only available for members and will not be downloaded' % unaccessible_videos)
+
+ entries = [
+ self.url_result('http://www.lynda.com/%s/%s-4.html' %
+ (course_path, video_id),
+ 'Lynda')
+ for video_id in videos]
+
+ course_title = course_json['Title']
+
+ return self.playlist_result(entries, course_id, course_title)
diff --git a/youtube_dl/extractor/macgamestore.py b/youtube_dl/extractor/macgamestore.py
new file mode 100644
index 000000000..b818cf50c
--- /dev/null
+++ b/youtube_dl/extractor/macgamestore.py
@@ -0,0 +1,43 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class MacGameStoreIE(InfoExtractor):
+ IE_NAME = 'macgamestore'
+ IE_DESC = 'MacGameStore trailers'
+ _VALID_URL = r'https?://www\.macgamestore\.com/mediaviewer\.php\?trailer=(?P<id>\d+)'
+
+ _TEST = {
+ 'url': 'http://www.macgamestore.com/mediaviewer.php?trailer=2450',
+ 'file': '2450.m4v',
+ 'md5': '8649b8ea684b6666b4c5be736ecddc61',
+ 'info_dict': {
+ 'title': 'Crow',
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, video_id, 'Downloading trailer page')
+
+ if re.search(r'>Missing Media<', webpage) is not None:
+ raise ExtractorError('Trailer %s does not exist' % video_id, expected=True)
+
+ video_title = self._html_search_regex(
+ r'<title>MacGameStore: (.*?) Trailer</title>', webpage, 'title')
+
+ video_url = self._html_search_regex(
+ r'(?s)<div\s+id="video-player".*?href="([^"]+)"\s*>',
+ webpage, 'video URL')
+
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'title': video_title
+ }
diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py
index 125d81551..7c54ea0f4 100644
--- a/youtube_dl/extractor/mixcloud.py
+++ b/youtube_dl/extractor/mixcloud.py
@@ -53,7 +53,7 @@ class MixcloudIE(InfoExtractor):
info = json.loads(json_data)
preview_url = self._search_regex(r'data-preview-url="(.+?)"', webpage, u'preview url')
- song_url = preview_url.replace('/previews/', '/cloudcasts/originals/')
+ song_url = preview_url.replace('/previews/', '/c/originals/')
template_url = re.sub(r'(stream\d*)', 'stream%d', song_url)
final_song_url = self._get_url(template_url)
if final_song_url is None:
diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py
index ed11f521a..f1cf41e2d 100644
--- a/youtube_dl/extractor/mtv.py
+++ b/youtube_dl/extractor/mtv.py
@@ -129,7 +129,7 @@ class MTVIE(MTVServicesInfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid')
- uri = mobj.group('mgid')
+ uri = mobj.groupdict().get('mgid')
if uri is None:
webpage = self._download_webpage(url, video_id)
diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py
index 71abd5013..e9ff8d1af 100644
--- a/youtube_dl/extractor/pornhd.py
+++ b/youtube_dl/extractor/pornhd.py
@@ -5,7 +5,7 @@ from ..utils import compat_urllib_parse
class PornHdIE(InfoExtractor):
- _VALID_URL = r'(?:http://)?(?:www\.)?pornhd\.com/videos/(?P<video_id>[0-9]+)/(?P<video_title>.+)'
+ _VALID_URL = r'(?:http://)?(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<video_id>[0-9]+)/(?P<video_title>.+)'
_TEST = {
u'url': u'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
u'file': u'1962.flv',
diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py
index e22ff9c38..951e977bd 100644
--- a/youtube_dl/extractor/soundcloud.py
+++ b/youtube_dl/extractor/soundcloud.py
@@ -29,7 +29,7 @@ class SoundcloudIE(InfoExtractor):
(?!sets/)(?P<title>[\w\d-]+)/?
(?P<token>[^?]+?)?(?:[?].*)?$)
|(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+))
- |(?P<widget>w\.soundcloud\.com/player/?.*?url=.*)
+ |(?P<player>(?:w|player|p.)\.soundcloud\.com/player/?.*?url=.*)
)
'''
IE_NAME = u'soundcloud'
@@ -193,7 +193,7 @@ class SoundcloudIE(InfoExtractor):
if track_id is not None:
info_json_url = 'http://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID
full_title = track_id
- elif mobj.group('widget'):
+ elif mobj.group('player'):
query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
return self.url_result(query['url'][0], ie='Soundcloud')
else:
diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py
index 584550455..bc31c2e64 100644
--- a/youtube_dl/extractor/wistia.py
+++ b/youtube_dl/extractor/wistia.py
@@ -44,6 +44,7 @@ class WistiaIE(InfoExtractor):
'height': a['height'],
'filesize': a['size'],
'ext': a['ext'],
+ 'preference': 1 if atype == 'original' else None,
})
self._sort_formats(formats)
diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index b0e29c2a8..9424d5e26 100644
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -194,6 +194,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
'137': {'ext': 'mp4', 'height': 1080, 'resolution': '1080p', 'format_note': 'DASH video', 'preference': -40},
'138': {'ext': 'mp4', 'height': 1081, 'resolution': '>1080p', 'format_note': 'DASH video', 'preference': -40},
'160': {'ext': 'mp4', 'height': 192, 'resolution': '192p', 'format_note': 'DASH video', 'preference': -40},
+ '264': {'ext': 'mp4', 'height': 1080, 'resolution': '1080p', 'format_note': 'DASH video', 'preference': -40},
# Dash mp4 audio
'139': {'ext': 'm4a', 'format_note': 'DASH audio', 'vcodec': 'none', 'abr': 48, 'preference': -50},
generated by cgit v1.2.3 (git 2.26.2) at 2024-11-20 15:56:30 +0000