Merge remote-tracking branch 'upstream/master'
Conflicts: youtube_dl/extractor/jeuxvideo.pypull/1293/head
Pierre Rudloff
11 years ago
commit
8d212e604a
@ -0,0 +1,34 @@
|
||||
import re
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class PBSIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://video.pbs.org/video/(?P<id>\d+)/?'
|
||||
|
||||
_TEST = {
|
||||
u'url': u'http://video.pbs.org/video/2365006249/',
|
||||
u'file': u'2365006249.mp4',
|
||||
u'md5': 'ce1888486f0908d555a8093cac9a7362',
|
||||
u'info_dict': {
|
||||
u'title': u'A More Perfect Union',
|
||||
u'description': u'md5:ba0c207295339c8d6eced00b7c363c6a',
|
||||
u'duration': 3190,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id
|
||||
info_page = self._download_webpage(info_url, video_id)
|
||||
info =json.loads(info_page)
|
||||
return {'id': video_id,
|
||||
'title': info['title'],
|
||||
'url': info['alternate_encoding']['url'],
|
||||
'ext': 'mp4',
|
||||
'description': info['program'].get('description'),
|
||||
'thumbnail': info.get('image_url'),
|
||||
'duration': info.get('duration'),
|
||||
}
|
||||
@ -0,0 +1,113 @@
|
||||
# encoding: utf-8
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
ExtractorError,
|
||||
)
|
||||
|
||||
class RTLnowIE(InfoExtractor):
|
||||
"""Information Extractor for RTLnow, RTL2now and VOXnow"""
|
||||
_VALID_URL = r'(?:http://)?(?P<url>(?P<base_url>rtl(?:(?P<is_rtl2>2)|-)now\.rtl(?(is_rtl2)2|)\.de/|(?:www\.)?voxnow\.de/)[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?(?:container_id|film_id)=(?P<video_id>[0-9]+)&player=1(?:&season=[0-9]+)?(?:&.*)?)'
|
||||
_TESTS = [{
|
||||
u'url': u'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1',
|
||||
u'file': u'90419.flv',
|
||||
u'info_dict': {
|
||||
u'upload_date': u'20070416',
|
||||
u'title': u'Ahornallee - Folge 1 - Der Einzug',
|
||||
u'description': u'Folge 1 - Der Einzug',
|
||||
},
|
||||
u'params': {
|
||||
u'skip_download': True,
|
||||
},
|
||||
u'skip': u'Only works from Germany',
|
||||
},
|
||||
{
|
||||
u'url': u'http://rtl2now.rtl2.de/aerger-im-revier/episode-15-teil-1.php?film_id=69756&player=1&season=2&index=5',
|
||||
u'file': u'69756.flv',
|
||||
u'info_dict': {
|
||||
u'upload_date': u'20120519',
|
||||
u'title': u'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit...',
|
||||
u'description': u'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit u.a.',
|
||||
u'thumbnail': u'http://autoimg.static-fra.de/rtl2now/219850/1500x1500/image2.jpg',
|
||||
},
|
||||
u'params': {
|
||||
u'skip_download': True,
|
||||
},
|
||||
u'skip': u'Only works from Germany',
|
||||
},
|
||||
{
|
||||
u'url': u'www.voxnow.de/voxtours/suedafrika-reporter-ii.php?film_id=13883&player=1&season=17',
|
||||
u'file': u'13883.flv',
|
||||
u'info_dict': {
|
||||
u'upload_date': u'20090627',
|
||||
u'title': u'Voxtours - Südafrika-Reporter II',
|
||||
u'description': u'Südafrika-Reporter II',
|
||||
},
|
||||
u'params': {
|
||||
u'skip_download': True,
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self,url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
|
||||
webpage_url = u'http://' + mobj.group('url')
|
||||
video_page_url = u'http://' + mobj.group('base_url')
|
||||
video_id = mobj.group(u'video_id')
|
||||
|
||||
webpage = self._download_webpage(webpage_url, video_id)
|
||||
|
||||
note_m = re.search(r'''(?sx)
|
||||
<div[ ]style="margin-left:[ ]20px;[ ]font-size:[ ]13px;">(.*?)
|
||||
<div[ ]id="playerteaser">''', webpage)
|
||||
if note_m:
|
||||
msg = clean_html(note_m.group(1))
|
||||
raise ExtractorError(msg)
|
||||
|
||||
video_title = self._html_search_regex(r'<title>(?P<title>[^<]+)</title>',
|
||||
webpage, u'title')
|
||||
playerdata_url = self._html_search_regex(r'\'playerdata\': \'(?P<playerdata_url>[^\']+)\'',
|
||||
webpage, u'playerdata_url')
|
||||
|
||||
playerdata = self._download_webpage(playerdata_url, video_id)
|
||||
mobj = re.search(r'<title><!\[CDATA\[(?P<description>.+?)\s+- (?:Sendung )?vom (?P<upload_date_d>[0-9]{2})\.(?P<upload_date_m>[0-9]{2})\.(?:(?P<upload_date_Y>[0-9]{4})|(?P<upload_date_y>[0-9]{2})) [0-9]{2}:[0-9]{2} Uhr\]\]></title>', playerdata)
|
||||
if mobj:
|
||||
video_description = mobj.group(u'description')
|
||||
if mobj.group('upload_date_Y'):
|
||||
video_upload_date = mobj.group('upload_date_Y')
|
||||
else:
|
||||
video_upload_date = u'20' + mobj.group('upload_date_y')
|
||||
video_upload_date += mobj.group('upload_date_m')+mobj.group('upload_date_d')
|
||||
else:
|
||||
video_description = None
|
||||
video_upload_date = None
|
||||
self._downloader.report_warning(u'Unable to extract description and upload date')
|
||||
|
||||
# Thumbnail: not every video has an thumbnail
|
||||
mobj = re.search(r'<meta property="og:image" content="(?P<thumbnail>[^"]+)">', webpage)
|
||||
if mobj:
|
||||
video_thumbnail = mobj.group(u'thumbnail')
|
||||
else:
|
||||
video_thumbnail = None
|
||||
|
||||
mobj = re.search(r'<filename [^>]+><!\[CDATA\[(?P<url>rtmpe://(?:[^/]+/){2})(?P<play_path>[^\]]+)\]\]></filename>', playerdata)
|
||||
if mobj is None:
|
||||
raise ExtractorError(u'Unable to extract media URL')
|
||||
video_url = mobj.group(u'url')
|
||||
video_play_path = u'mp4:' + mobj.group(u'play_path')
|
||||
video_player_url = video_page_url + u'includes/vodplayer.swf'
|
||||
|
||||
return [{
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'play_path': video_play_path,
|
||||
'page_url': video_page_url,
|
||||
'player_url': video_player_url,
|
||||
'ext': 'flv',
|
||||
'title': video_title,
|
||||
'description': video_description,
|
||||
'upload_date': video_upload_date,
|
||||
'thumbnail': video_thumbnail,
|
||||
}]
|
||||
@ -0,0 +1,23 @@
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class SlashdotIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://tv.slashdot.org/video/\?embed=(?P<id>.*?)(&|$)'
|
||||
|
||||
_TEST = {
|
||||
u'url': u'http://tv.slashdot.org/video/?embed=JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz',
|
||||
u'file': u'JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz.mp4',
|
||||
u'md5': u'd2222e7a4a4c1541b3e0cf732fb26735',
|
||||
u'info_dict': {
|
||||
u'title': u' Meet the Stampede Supercomputing Cluster\'s Administrator',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
ooyala_url = self._search_regex(r'<script src="(.*?)"', webpage, 'ooyala url')
|
||||
return self.url_result(ooyala_url, 'Ooyala')
|
||||
@ -1,2 +1,2 @@
|
||||
|
||||
__version__ = '2013.08.17'
|
||||
__version__ = '2013.08.21'
|
||||
|
||||
Loading…
Reference in New Issue