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/addanime.py75
-rw-r--r--youtube_dl/extractor/appletrailers.py166
-rw-r--r--youtube_dl/extractor/canalc2.py35
-rw-r--r--youtube_dl/extractor/canalplus.py2
-rw-r--r--youtube_dl/extractor/cnn.py58
-rw-r--r--youtube_dl/extractor/common.py16
-rw-r--r--youtube_dl/extractor/generic.py7
-rw-r--r--youtube_dl/extractor/googleplus.py4
-rw-r--r--youtube_dl/extractor/hark.py22
-rw-r--r--youtube_dl/extractor/kankan.py6
-rw-r--r--youtube_dl/extractor/mit.py76
-rw-r--r--youtube_dl/extractor/nbc.py33
-rw-r--r--youtube_dl/extractor/sohu.py90
-rw-r--r--youtube_dl/extractor/trilulilu.py73
-rw-r--r--youtube_dl/extractor/wat.py1
-rw-r--r--youtube_dl/extractor/youporn.py18
-rw-r--r--youtube_dl/extractor/youtube.py2
18 files changed, 665 insertions, 31 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index f71ae2713..6b5037c8c 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -1,3 +1,5 @@
+from .appletrailers import AppleTrailersIE
+from .addanime import AddAnimeIE
from .archiveorg import ArchiveOrgIE
from .ard import ARDIE
from .arte import ArteTvIE
@@ -6,7 +8,10 @@ from .bandcamp import BandcampIE
from .bliptv import BlipTVIE, BlipTVUserIE
from .breakcom import BreakIE
from .brightcove import BrightcoveIE
+from .c56 import C56IE
from .canalplus import CanalplusIE
+from .canalc2 import Canalc2IE
+from .cnn import CNNIE
from .collegehumor import CollegeHumorIE
from .comedycentral import ComedyCentralIE
from .condenast import CondeNastIE
@@ -45,12 +50,14 @@ from .keek import KeekIE
from .liveleak import LiveLeakIE
from .livestream import LivestreamIE
from .metacafe import MetacafeIE
+from .mit import TechTVMITIE, MITIE
from .mixcloud import MixcloudIE
from .mtv import MTVIE
from .muzu import MuzuTVIE
from .myspass import MySpassIE
from .myvideo import MyVideoIE
from .nba import NBAIE
+from .nbc import NBCNewsIE
from .ooyala import OoyalaIE
from .pbs import PBSIE
from .photobucket import PhotobucketIE
@@ -63,6 +70,7 @@ from .roxwel import RoxwelIE
from .rtlnow import RTLnowIE
from .sina import SinaIE
from .slashdot import SlashdotIE
+from .sohu import SohuIE
from .soundcloud import SoundcloudIE, SoundcloudSetIE
from .spiegel import SpiegelIE
from .stanfordoc import StanfordOpenClassroomIE
@@ -73,18 +81,18 @@ from .ted import TEDIE
from .tf1 import TF1IE
from .thisav import ThisAVIE
from .traileraddict import TrailerAddictIE
+from .trilulilu import TriluliluIE
from .tudou import TudouIE
from .tumblr import TumblrIE
from .tutv import TutvIE
-from .ustream import UstreamIE
from .unistra import UnistraIE
+from .ustream import UstreamIE
from .vbox7 import Vbox7IE
from .veoh import VeohIE
from .vevo import VevoIE
from .videofyme import VideofyMeIE
from .vimeo import VimeoIE, VimeoChannelIE
from .vine import VineIE
-from .c56 import C56IE
from .wat import WatIE
from .weibo import WeiboIE
from .wimp import WimpIE
diff --git a/youtube_dl/extractor/addanime.py b/youtube_dl/extractor/addanime.py
new file mode 100644
index 000000000..82a785a19
--- /dev/null
+++ b/youtube_dl/extractor/addanime.py
@@ -0,0 +1,75 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_HTTPError,
+ compat_str,
+ compat_urllib_parse,
+ compat_urllib_parse_urlparse,
+
+ ExtractorError,
+)
+
+
+class AddAnimeIE(InfoExtractor):
+
+ _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)'
+ IE_NAME = u'AddAnime'
+ _TEST = {
+ u'url': u'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
+ u'file': u'24MR3YO5SAS9.flv',
+ u'md5': u'1036a0e0cd307b95bd8a8c3a5c8cfaf1',
+ u'info_dict': {
+ u"description": u"One Piece 606",
+ u"title": u"One Piece 606"
+ }
+ }
+
+ def _real_extract(self, url):
+ try:
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('video_id')
+ webpage = self._download_webpage(url, video_id)
+ except ExtractorError as ee:
+ if not isinstance(ee.cause, compat_HTTPError):
+ raise
+
+ redir_webpage = ee.cause.read().decode('utf-8')
+ action = self._search_regex(
+ r'<form id="challenge-form" action="([^"]+)"',
+ redir_webpage, u'Redirect form')
+ vc = self._search_regex(
+ r'<input type="hidden" name="jschl_vc" value="([^"]+)"/>',
+ redir_webpage, u'redirect vc value')
+ av = re.search(
+ r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);',
+ redir_webpage)
+ if av is None:
+ raise ExtractorError(u'Cannot find redirect math task')
+ av_res = int(av.group(1)) + int(av.group(2)) * int(av.group(3))
+
+ parsed_url = compat_urllib_parse_urlparse(url)
+ av_val = av_res + len(parsed_url.netloc)
+ confirm_url = (
+ parsed_url.scheme + u'://' + parsed_url.netloc +
+ action + '?' +
+ compat_urllib_parse.urlencode({
+ 'jschl_vc': vc, 'jschl_answer': compat_str(av_val)}))
+ self._download_webpage(
+ confirm_url, video_id,
+ note=u'Confirming after redirect')
+ webpage = self._download_webpage(url, video_id)
+
+ video_url = self._search_regex(r"var normal_video_file = '(.*?)';",
+ webpage, u'video file URL')
+ video_title = self._og_search_title(webpage)
+ video_description = self._og_search_description(webpage)
+
+ return {
+ '_type': 'video',
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'flv',
+ 'title': video_title,
+ 'description': video_description
+ }
diff --git a/youtube_dl/extractor/appletrailers.py b/youtube_dl/extractor/appletrailers.py
new file mode 100644
index 000000000..8b191c196
--- /dev/null
+++ b/youtube_dl/extractor/appletrailers.py
@@ -0,0 +1,166 @@
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+ determine_ext,
+)
+
+
+class AppleTrailersIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?trailers.apple.com/trailers/(?P<company>[^/]+)/(?P<movie>[^/]+)'
+ _TEST = {
+ u"url": u"http://trailers.apple.com/trailers/wb/manofsteel/",
+ u"playlist": [
+ {
+ u"file": u"manofsteel-trailer4.mov",
+ u"md5": u"11874af099d480cc09e103b189805d5f",
+ u"info_dict": {
+ u"duration": 111,
+ u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_11624.jpg",
+ u"title": u"Trailer 4",
+ u"upload_date": u"20130523",
+ u"uploader_id": u"wb",
+ },
+ },
+ {
+ u"file": u"manofsteel-trailer3.mov",
+ u"md5": u"07a0a262aae5afe68120eed61137ab34",
+ u"info_dict": {
+ u"duration": 182,
+ u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_10793.jpg",
+ u"title": u"Trailer 3",
+ u"upload_date": u"20130417",
+ u"uploader_id": u"wb",
+ },
+ },
+ {
+ u"file": u"manofsteel-trailer.mov",
+ u"md5": u"e401fde0813008e3307e54b6f384cff1",
+ u"info_dict": {
+ u"duration": 148,
+ u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_8703.jpg",
+ u"title": u"Trailer",
+ u"upload_date": u"20121212",
+ u"uploader_id": u"wb",
+ },
+ },
+ {
+ u"file": u"manofsteel-teaser.mov",
+ u"md5": u"76b392f2ae9e7c98b22913c10a639c97",
+ u"info_dict": {
+ u"duration": 93,
+ u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_6899.jpg",
+ u"title": u"Teaser",
+ u"upload_date": u"20120721",
+ u"uploader_id": u"wb",
+ },
+ }
+ ]
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ movie = mobj.group('movie')
+ uploader_id = mobj.group('company')
+
+ playlist_url = url.partition(u'?')[0] + u'/includes/playlists/web.inc'
+ playlist_snippet = self._download_webpage(playlist_url, movie)
+ playlist_cleaned = re.sub(r'(?s)<script>.*?</script>', u'', playlist_snippet)
+ playlist_html = u'<html>' + playlist_cleaned + u'</html>'
+
+ size_cache = {}
+
+ doc = xml.etree.ElementTree.fromstring(playlist_html)
+ playlist = []
+ for li in doc.findall('./div/ul/li'):
+ title = li.find('.//h3').text
+ video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower()
+ thumbnail = li.find('.//img').attrib['src']
+
+ date_el = li.find('.//p')
+ upload_date = None
+ m = re.search(r':\s?(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<year>[0-9]{2})', date_el.text)
+ if m:
+ upload_date = u'20' + m.group('year') + m.group('month') + m.group('day')
+ runtime_el = date_el.find('./br')
+ m = re.search(r':\s?(?P<minutes>[0-9]+):(?P<seconds>[0-9]{1,2})', runtime_el.tail)
+ duration = None
+ if m:
+ duration = 60 * int(m.group('minutes')) + int(m.group('seconds'))
+
+ formats = []
+ for formats_el in li.findall('.//a'):
+ if formats_el.attrib['class'] != 'OverlayPanel':
+ continue
+ target = formats_el.attrib['target']
+
+ format_code = formats_el.text
+ if 'Automatic' in format_code:
+ continue
+
+ size_q = formats_el.attrib['href']
+ size_id = size_q.rpartition('#videos-')[2]
+ if size_id not in size_cache:
+ size_url = url + size_q
+ sizepage_html = self._download_webpage(
+ size_url, movie,
+ note=u'Downloading size info %s' % size_id,
+ errnote=u'Error while downloading size info %s' % size_id,
+ )
+ _doc = xml.etree.ElementTree.fromstring(sizepage_html)
+ size_cache[size_id] = _doc
+
+ sizepage_doc = size_cache[size_id]
+ links = sizepage_doc.findall('.//{http://www.w3.org/1999/xhtml}ul/{http://www.w3.org/1999/xhtml}li/{http://www.w3.org/1999/xhtml}a')
+ for vid_a in links:
+ href = vid_a.get('href')
+ if not href.endswith(target):
+ continue
+ detail_q = href.partition('#')[0]
+ detail_url = url + '/' + detail_q
+
+ m = re.match(r'includes/(?P<detail_id>[^/]+)/', detail_q)
+ detail_id = m.group('detail_id')
+
+ detail_html = self._download_webpage(
+ detail_url, movie,
+ note=u'Downloading detail %s %s' % (detail_id, size_id),
+ errnote=u'Error while downloading detail %s %s' % (detail_id, size_id)
+ )
+ detail_doc = xml.etree.ElementTree.fromstring(detail_html)
+ movie_link_el = detail_doc.find('.//{http://www.w3.org/1999/xhtml}a')
+ assert movie_link_el.get('class') == 'movieLink'
+ movie_link = movie_link_el.get('href').partition('?')[0].replace('_', '_h')
+ ext = determine_ext(movie_link)
+ assert ext == 'mov'
+
+ formats.append({
+ 'format': format_code,
+ 'ext': ext,
+ 'url': movie_link,
+ })
+
+ info = {
+ '_type': 'video',
+ 'id': video_id,
+ 'title': title,
+ 'formats': formats,
+ 'title': title,
+ 'duration': duration,
+ 'thumbnail': thumbnail,
+ 'upload_date': upload_date,
+ 'uploader_id': uploader_id,
+ 'user_agent': 'QuickTime compatible (youtube-dl)',
+ }
+ # TODO: Remove when #980 has been merged
+ info['url'] = formats[-1]['url']
+ info['ext'] = formats[-1]['ext']
+
+ playlist.append(info)
+
+ return {
+ '_type': 'playlist',
+ 'id': movie,
+ 'entries': playlist,
+ }
diff --git a/youtube_dl/extractor/canalc2.py b/youtube_dl/extractor/canalc2.py
new file mode 100644
index 000000000..50832217a
--- /dev/null
+++ b/youtube_dl/extractor/canalc2.py
@@ -0,0 +1,35 @@
+# coding: utf-8
+import re
+
+from .common import InfoExtractor
+
+
+class Canalc2IE(InfoExtractor):
+ _IE_NAME = 'canalc2.tv'
+ _VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?idVideo=(\d+)&voir=oui'
+
+ _TEST = {
+ u'url': u'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
+ u'file': u'12163.mp4',
+ u'md5': u'060158428b650f896c542dfbb3d6487f',
+ u'info_dict': {
+ u'title': u'Terrasses du Numérique'
+ }
+ }
+
+ def _real_extract(self, url):
+ video_id = re.match(self._VALID_URL, url).group(1)
+ webpage = self._download_webpage(url, video_id)
+ file_name = self._search_regex(
+ r"so\.addVariable\('file','(.*?)'\);",
+ webpage, 'file name')
+ video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name
+
+ title = self._html_search_regex(
+ r'class="evenement8">(.*?)</a>', webpage, u'title')
+
+ return {'id': video_id,
+ 'ext': 'mp4',
+ 'url': video_url,
+ 'title': title,
+ }
diff --git a/youtube_dl/extractor/canalplus.py b/youtube_dl/extractor/canalplus.py
index 3b1c88876..1f02519a0 100644
--- a/youtube_dl/extractor/canalplus.py
+++ b/youtube_dl/extractor/canalplus.py
@@ -5,7 +5,7 @@ from .common import InfoExtractor
from ..utils import unified_strdate
class CanalplusIE(InfoExtractor):
- _VALID_URL = r'https?://www\.canalplus\.fr/.*?\?vid=(?P<id>\d+)'
+ _VALID_URL = r'https?://(www\.canalplus\.fr/.*?\?vid=|player\.canalplus\.fr/#/)(?P<id>\d+)'
_VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s'
IE_NAME = u'canalplus.fr'
diff --git a/youtube_dl/extractor/cnn.py b/youtube_dl/extractor/cnn.py
new file mode 100644
index 000000000..a79f881cd
--- /dev/null
+++ b/youtube_dl/extractor/cnn.py
@@ -0,0 +1,58 @@
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import determine_ext
+
+
+class CNNIE(InfoExtractor):
+ _VALID_URL = r'''(?x)https?://(edition\.)?cnn\.com/video/(data/.+?|\?)/
+ (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn|(?=&)))'''
+
+ _TESTS = [{
+ u'url': u'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
+ u'file': u'sports_2013_06_09_nadal-1-on-1.cnn.mp4',
+ u'md5': u'3e6121ea48df7e2259fe73a0628605c4',
+ u'info_dict': {
+ u'title': u'Nadal wins 8th French Open title',
+ u'description': u'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.',
+ },
+ },
+ {
+ u"url": u"http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29",
+ u"file": u"us_2013_08_21_sot-student-gives-epic-speech.georgia-institute-of-technology.mp4",
+ u"md5": u"b5cc60c60a3477d185af8f19a2a26f4e",
+ u"info_dict": {
+ u"title": "Student's epic speech stuns new freshmen",
+ u"description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\""
+ }
+ }]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ path = mobj.group('path')
+ page_title = mobj.group('title')
+ info_url = u'http://cnn.com/video/data/3.0/%s/index.xml' % path
+ info_xml = self._download_webpage(info_url, page_title)
+ info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
+
+ formats = []
+ for f in info.findall('files/file'):
+ mf = re.match(r'(\d+)x(\d+)(?:_(.*)k)?',f.attrib['bitrate'])
+ if mf is not None:
+ formats.append((int(mf.group(1)), int(mf.group(2)), int(mf.group(3) or 0), f.text))
+ formats = sorted(formats)
+ (_,_,_, video_path) = formats[-1]
+ video_url = 'http://ht.cdn.turner.com/cnn/big%s' % video_path
+
+ thumbnails = sorted([((int(t.attrib['height']),int(t.attrib['width'])), t.text) for t in info.findall('images/image')])
+ thumbs_dict = [{'resolution': res, 'url': t_url} for (res, t_url) in thumbnails]
+
+ return {'id': info.attrib['id'],
+ 'title': info.find('headline').text,
+ 'url': video_url,
+ 'ext': determine_ext(video_url),
+ 'thumbnail': thumbnails[-1][1],
+ 'thumbnails': thumbs_dict,
+ 'description': info.find('description').text,
+ }
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index 52c4483c9..a2986cebe 100644
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -114,6 +114,11 @@ class InfoExtractor(object):
"""Real extraction process. Redefine in subclasses."""
pass
+ @classmethod
+ def ie_key(cls):
+ """A string for getting the InfoExtractor with get_info_extractor"""
+ return cls.__name__[:-2]
+
@property
def IE_NAME(self):
return type(self).__name__[:-2]
@@ -129,7 +134,7 @@ class InfoExtractor(object):
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
if errnote is None:
errnote = u'Unable to download webpage'
- raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2])
+ raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2], cause=err)
def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None):
""" Returns a tuple (page content as string, URL handle) """
@@ -140,12 +145,17 @@ class InfoExtractor(object):
urlh = self._request_webpage(url_or_request, video_id, note, errnote)
content_type = urlh.headers.get('Content-Type', '')
+ webpage_bytes = urlh.read()
m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
if m:
encoding = m.group(1)
else:
- encoding = 'utf-8'
- webpage_bytes = urlh.read()
+ m = re.search(br'<meta[^>]+charset="?([^"]+)[ /">]',
+ webpage_bytes[:1024])
+ if m:
+ encoding = m.group(1).decode('ascii')
+ else:
+ encoding = 'utf-8'
if self._downloader.params.get('dump_intermediate_pages', False):
try:
url = url_or_request.get_full_url()
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index d034a11bb..dc4dea4ad 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -7,8 +7,8 @@ from .common import InfoExtractor
from ..utils import (
compat_urllib_error,
compat_urllib_parse,
- compat_urllib_parse_urlparse,
compat_urllib_request,
+ compat_urlparse,
ExtractorError,
)
@@ -163,10 +163,7 @@ class GenericIE(InfoExtractor):
raise ExtractorError(u'Invalid URL: %s' % url)
video_url = compat_urllib_parse.unquote(mobj.group(1))
- if video_url.startswith('//'):
- video_url = compat_urllib_parse_urlparse(url).scheme + ':' + video_url
- if '://' not in video_url:
- video_url = url + ('' if url.endswith('/') else '/') + video_url
+ video_url = compat_urlparse.urljoin(url, video_url)
video_id = os.path.basename(video_url)
# here's a fun little line of code for you:
diff --git a/youtube_dl/extractor/googleplus.py b/youtube_dl/extractor/googleplus.py
index 9f7fc19a4..f1cd88983 100644
--- a/youtube_dl/extractor/googleplus.py
+++ b/youtube_dl/extractor/googleplus.py
@@ -57,8 +57,8 @@ class GooglePlusIE(InfoExtractor):
webpage, 'title', default=u'NA')
# Step 2, Simulate clicking the image box to launch video
- DOMAIN = 'https://plus.google.com'
- video_page = self._search_regex(r'<a href="((?:%s)?/photos/.*?)"' % re.escape(DOMAIN),
+ DOMAIN = 'https://plus.google.com/'
+ video_page = self._search_regex(r'<a href="((?:%s)?photos/.*?)"' % re.escape(DOMAIN),
webpage, u'video page URL')
if not video_page.startswith(DOMAIN):
video_page = DOMAIN + video_page
diff --git a/youtube_dl/extractor/hark.py b/youtube_dl/extractor/hark.py
index ab0a69697..5bdd08afa 100644
--- a/youtube_dl/extractor/hark.py
+++ b/youtube_dl/extractor/hark.py
@@ -1,6 +1,7 @@
# -*- coding: utf-8 -*-
import re
+import json
from .common import InfoExtractor
from ..utils import determine_ext
@@ -12,24 +13,25 @@ class HarkIE(InfoExtractor):
u'file': u'mmbzyhkgny.mp3',
u'md5': u'6783a58491b47b92c7c1af5a77d4cbee',
u'info_dict': {
- u"title": u"Obama: 'Beyond The Afghan Theater, We Only Target Al Qaeda' On May 23, 2013 ",
+ u'title': u"Obama: 'Beyond The Afghan Theater, We Only Target Al Qaeda' on May 23, 2013",
+ u'description': u'President Barack Obama addressed the nation live on May 23, 2013 in a speech aimed at addressing counter-terrorism policies including the use of drone strikes, detainees at Guantanamo Bay prison facility, and American citizens who are terrorists.',
+ u'duration': 11,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1)
- embed_url = "http://www.hark.com/clips/%s/homepage_embed" %(video_id)
- webpage = self._download_webpage(embed_url, video_id)
-
- final_url = self._search_regex(r'src="(.+?).mp3"',
- webpage, 'video url')+'.mp3'
- title = self._html_search_regex(r'<title>(.+?)</title>',
- webpage, 'video title').replace(' Sound Clip and Quote - Hark','').replace(
- 'Sound Clip , Quote, MP3, and Ringtone - Hark','')
+ json_url = "http://www.hark.com/clips/%s.json" %(video_id)
+ info_json = self._download_webpage(json_url, video_id)
+ info = json.loads(info_json)
+ final_url = info['url']
return {'id': video_id,
'url' : final_url,
- 'title': title,
+ 'title': info['name'],
'ext': determine_ext(final_url),
+ 'description': info['description'],
+ 'thumbnail': info['image_original'],
+ 'duration': info['duration'],
}
diff --git a/youtube_dl/extractor/kankan.py b/youtube_dl/extractor/kankan.py
index 8537ba584..445d46501 100644
--- a/youtube_dl/extractor/kankan.py
+++ b/youtube_dl/extractor/kankan.py
@@ -21,8 +21,10 @@ class KankanIE(InfoExtractor):
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
- title = self._search_regex(r'G_TITLE=[\'"](.+?)[\'"]', webpage, u'video title')
- gcid = self._search_regex(r'lurl:[\'"]http://.+?/.+?/(.+?)/', webpage, u'gcid')
+ title = self._search_regex(r'(?:G_TITLE=|G_MOVIE_TITLE = )[\'"](.+?)[\'"]', webpage, u'video title')
+ surls = re.search(r'surls:\[\'.+?\'\]|lurl:\'.+?\.flv\'', webpage).group(0)
+ gcids = re.findall(r"http://.+?/.+?/(.+?)/", surls)
+ gcid = gcids[-1]
video_info_page = self._download_webpage('http://p2s.cl.kankan.com/getCdnresource_flv?gcid=%s' % gcid,
video_id, u'Downloading video url info')
diff --git a/youtube_dl/extractor/mit.py b/youtube_dl/extractor/mit.py
new file mode 100644
index 000000000..d09d03e36
--- /dev/null
+++ b/youtube_dl/extractor/mit.py
@@ -0,0 +1,76 @@
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+ clean_html,
+ get_element_by_id,
+)
+
+
+class TechTVMITIE(InfoExtractor):
+ IE_NAME = u'techtv.mit.edu'
+ _VALID_URL = r'https?://techtv\.mit\.edu/(videos|embeds)/(?P<id>\d+)'
+
+ _TEST = {
+ u'url': u'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
+ u'file': u'25418.mp4',
+ u'md5': u'1f8cb3e170d41fd74add04d3c9330e5f',
+ u'info_dict': {
+ u'title': u'MIT DNA Learning Center Set',
+ u'description': u'md5:82313335e8a8a3f243351ba55bc1b474',
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ webpage = self._download_webpage(
+ 'http://techtv.mit.edu/videos/%s' % video_id, video_id)
+ embed_page = self._download_webpage(
+ 'http://techtv.mit.edu/embeds/%s/' % video_id, video_id,
+ note=u'Downloading embed page')
+
+ base_url = self._search_regex(r'ipadUrl: \'(.+?cloudfront.net/)',
+ embed_page, u'base url')
+ formats_json = self._search_regex(r'bitrates: (\[.+?\])', embed_page,
+ u'video formats')
+ formats = json.loads(formats_json)
+ formats = sorted(formats, key=lambda f: f['bitrate'])
+
+ title = get_element_by_id('edit-title', webpage)
+ description = clean_html(get_element_by_id('edit-description', webpage))
+ thumbnail = self._search_regex(r'playlist:.*?url: \'(.+?)\'',
+ embed_page, u'thumbnail', flags=re.DOTALL)
+
+ return {'id': video_id,
+ 'title': title,
+ 'url': base_url + formats[-1]['url'].replace('mp4:', ''),
+ 'ext': 'mp4',
+ 'description': description,
+ 'thumbnail': thumbnail,
+ }
+
+
+class MITIE(TechTVMITIE):
+ IE_NAME = u'video.mit.edu'
+ _VALID_URL = r'https?://video\.mit\.edu/watch/(?P<title>[^/]+)'
+
+ _TEST = {
+ u'url': u'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
+ u'file': u'21783.mp4',
+ u'md5': u'7db01d5ccc1895fc5010e9c9e13648da',
+ u'info_dict': {
+ u'title': u'The Government is Profiling You',
+ u'description': u'md5:ad5795fe1e1623b73620dbfd47df9afd',
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ page_title = mobj.group('title')
+ webpage = self._download_webpage(url, page_title)
+ self.to_screen('%s: Extracting %s url' % (page_title, TechTVMITIE.IE_NAME))
+ embed_url = self._search_regex(r'<iframe .*?src="(.+?)"', webpage,
+ u'embed url')
+ return self.url_result(embed_url, ie='TechTVMIT')
diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py
new file mode 100644
index 000000000..3bc9dae6d
--- /dev/null
+++ b/youtube_dl/extractor/nbc.py
@@ -0,0 +1,33 @@
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import find_xpath_attr, compat_str
+
+
+class NBCNewsIE(InfoExtractor):
+ _VALID_URL = r'https?://www\.nbcnews\.com/video/.+?/(?P<id>\d+)'
+
+ _TEST = {
+ u'url': u'http://www.nbcnews.com/video/nbc-news/52753292',
+ u'file': u'52753292.flv',
+ u'md5': u'47abaac93c6eaf9ad37ee6c4463a5179',
+ u'info_dict': {
+ u'title': u'Crew emerges after four-month Mars food study',
+ u'description': u'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ info_xml = self._download_webpage('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
+ info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8')).find('video')
+
+ return {'id': video_id,
+ 'title': info.find('headline').text,
+ 'ext': 'flv',
+ 'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
+ 'description': compat_str(info.find('caption').text),
+ 'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
+ }
diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py
new file mode 100644
index 000000000..77bb0a8dc
--- /dev/null
+++ b/youtube_dl/extractor/sohu.py
@@ -0,0 +1,90 @@
+# encoding: utf-8
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class SohuIE(InfoExtractor):
+ _VALID_URL = r'https?://tv\.sohu\.com/\d+?/n(?P<id>\d+)\.shtml.*?'
+
+ _TEST = {
+ u'url': u'http://tv.sohu.com/20130724/n382479172.shtml#super',
+ u'file': u'382479172.mp4',
+ u'md5': u'bde8d9a6ffd82c63a1eefaef4eeefec7',
+ u'info_dict': {
+ u'title': u'MV：Far East Movement《The Illest》',
+ },
+ }
+
+ def _real_extract(self, url):
+
+ def _fetch_data(vid_id):
+ base_data_url = u'http://hot.vrs.sohu.com/vrs_flash.action?vid='
+ data_url = base_data_url + str(vid_id)
+ data_json = self._download_webpage(
+ data_url, video_id,
+ note=u'Downloading JSON data for ' + str(vid_id))
+ return json.loads(data_json)
+
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, video_id)
+ raw_title = self._html_search_regex(r'(?s)<title>(.+?)</title>',
+ webpage, u'video title')
+ title = raw_title.partition('-')[0].strip()
+
+ vid = self._html_search_regex(r'var vid="(\d+)"', webpage,
+ u'video path')
+ data = _fetch_data(vid)
+
+ QUALITIES = ('ori', 'super', 'high', 'nor')
+ vid_ids = [data['data'][q + 'Vid']
+ for q in QUALITIES
+ if data['data'][q + 'Vid'] != 0]
+ if not vid_ids:
+ raise ExtractorError(u'No formats available for this video')
+
+ # For now, we just pick the highest available quality
+ vid_id = vid_ids[-1]
+
+ format_data = data if vid == vid_id else _fetch_data(vid_id)
+ part_count = format_data['data']['totalBlocks']
+ allot = format_data['allot']
+ prot = format_data['prot']
+ clipsURL = format_data['data']['clipsURL']
+ su = format_data['data']['su']
+
+ playlist = []
+ for i in range(part_count):
+ part_url = ('http://%s/?prot=%s&file=%s&new=%s' %
+ (allot, prot, clipsURL[i], su[i]))
+ part_str = self._download_webpage(
+ part_url, video_id,
+ note=u'Downloading part %d of %d' % (i+1, part_count))
+
+ part_info = part_str.split('|')
+ video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3])
+
+ video_info = {
+ 'id': '%s_part%02d' % (video_id, i + 1),
+ 'title': title,
+ 'url': video_url,
+ 'ext': 'mp4',
+ }
+ playlist.append(video_info)
+
+ if len(playlist) == 1:
+ info = playlist[0]
+ info['id'] = video_id
+ else:
+ info = {
+ '_type': 'playlist',
+ 'entries': playlist,
+ 'id': video_id,
+ }
+
+ return info
diff --git a/youtube_dl/extractor/trilulilu.py b/youtube_dl/extractor/trilulilu.py
new file mode 100644
index 000000000..f278951ba
--- /dev/null
+++ b/youtube_dl/extractor/trilulilu.py
@@ -0,0 +1,73 @@
+import json
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+
+
+class TriluliluIE(InfoExtractor):
+ _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?trilulilu\.ro/video-(?P<category>[^/]+)/(?P<video_id>[^/]+)'
+ _TEST = {
+ u"url": u"http://www.trilulilu.ro/video-animatie/big-buck-bunny-1",
+ u'file': u"big-buck-bunny-1.mp4",
+ u'info_dict': {
+ u"title": u"Big Buck Bunny",
+ u"description": u":) pentru copilul din noi",
+ },
+ # Server ignores Range headers (--test)
+ u"params": {
+ u"skip_download": True
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('video_id')
+
+ webpage = self._download_webpage(url, video_id)
+
+ title = self._og_search_title(webpage)
+ thumbnail = self._og_search_thumbnail(webpage)
+ description = self._og_search_description(webpage)
+
+ log_str = self._search_regex(
+ r'block_flash_vars[ ]=[ ]({[^}]+})', webpage, u'log info')
+ log = json.loads(log_str)
+
+ format_url = (u'http://fs%(server)s.trilulilu.ro/%(hash)s/'
+ u'video-formats2' % log)
+ format_str = self._download_webpage(
+ format_url, video_id,
+ note=u'Downloading formats',
+ errnote=u'Error while downloading formats')
+
+ format_doc = xml.etree.ElementTree.fromstring(format_str)
+
+ video_url_template = (
+ u'http://fs%(server)s.trilulilu.ro/stream.php?type=video'
+ u'&source=site&hash=%(hash)s&username=%(userid)s&'
+ u'key=ministhebest&format=%%s&sig=&exp=' %
+ log)
+ formats = [
+ {
+ 'format': fnode.text,
+ 'url': video_url_template % fnode.text,
+ }
+
+ for fnode in format_doc.findall('./formats/format')
+ ]
+
+ info = {
+ '_type': 'video',
+ 'id': video_id,
+ 'formats': formats,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ }
+
+ # TODO: Remove when #980 has been merged
+ info['url'] = formats[-1]['url']
+ info['ext'] = formats[-1]['format'].partition('-')[0]
+
+ return info
diff --git a/youtube_dl/extractor/wat.py b/youtube_dl/extractor/wat.py
index 7d228edac..29c25f0e3 100644
--- a/youtube_dl/extractor/wat.py
+++ b/youtube_dl/extractor/wat.py
@@ -6,7 +6,6 @@ import re
from .common import InfoExtractor
from ..utils import (
- compat_urllib_parse,
unified_strdate,
)
diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py
index d1156bf42..c85fd4b5a 100644
--- a/youtube_dl/extractor/youporn.py
+++ b/youtube_dl/extractor/youporn.py
@@ -12,14 +12,16 @@ from ..utils import (
unescapeHTML,
unified_strdate,
)
-
+from ..aes import (
+ aes_decrypt_text
+)
class YouPornIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)'
_TEST = {
u'url': u'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
u'file': u'505835.mp4',
- u'md5': u'c37ddbaaa39058c76a7e86c6813423c1',
+ u'md5': u'71ec5fcfddacf80f495efa8b6a8d9a89',
u'info_dict': {
u"upload_date": u"20101221",
u"description": u"Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?",
@@ -75,7 +77,15 @@ class YouPornIE(InfoExtractor):
# Get all of the links from the page
LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">'
links = re.findall(LINK_RE, download_list_html)
- if(len(links) == 0):
+
+ # Get link of hd video if available
+ mobj = re.search(r'var encryptedQuality720URL = \'(?P<encrypted_video_url>[a-zA-Z0-9+/]+={0,2})\';', webpage)
+ if mobj != None:
+ encrypted_video_url = mobj.group(u'encrypted_video_url')
+ video_url = aes_decrypt_text(encrypted_video_url, video_title, 32).decode('utf-8')
+ links = [video_url] + links
+
+ if not links:
raise ExtractorError(u'ERROR: no known formats available for video')
self.to_screen(u'Links found: %d' % len(links))
@@ -112,7 +122,7 @@ class YouPornIE(InfoExtractor):
self._print_formats(formats)
return
- req_format = self._downloader.params.get('format', None)
+ req_format = self._downloader.params.get('format', 'best')
self.to_screen(u'Format: %s' % req_format)
if req_format is None or req_format == 'best':
diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index af01c9da0..8e486afd0 100644
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -419,7 +419,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
elif len(s) == 89:
return s[84:78:-1] + s[87] + s[77:60:-1] + s[0] + s[59:3:-1]
elif len(s) == 88:
- return s[48] + s[81:67:-1] + s[82] + s[66:62:-1] + s[85] + s[61:48:-1] + s[67] + s[47:12:-1] + s[3] + s[11:3:-1] + s[2] + s[12]
+ return s[7:28] + s[87] + s[29:45] + s[55] + s[46:55] + s[2] + s[56:87] + s[28]
elif len(s) == 87:
return s[6:27] + s[4] + s[28:39] + s[27] + s[40:59] + s[2] + s[60:]
elif len(s) == 86:
generated by cgit v1.2.3 (git 2.26.2) at 2024-11-17 20:15:12 +0000