mirror of https://github.com/blackjack4494/yt-dlc
Add RTLnow extractor
Supports http://rtl2now.rtl2.de and http://rtl-now.rtl.de
This commit is contained in:
parent
67fb0c5495
commit
dbda1b5147
|
@ -0,0 +1,88 @@
|
|||
# encoding: utf-8
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import ExtractorError
|
||||
|
||||
class RTLnowIE(InfoExtractor):
|
||||
"""Information Extractor for RTL(2)now"""
|
||||
_VALID_URL = r'(?:http://)?(?P<url>(?P<base_url>rtl(?:(?P<is_rtl2>2)|-)now\.rtl(?(is_rtl2)2|)\.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'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,
|
||||
},
|
||||
},]
|
||||
|
||||
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)
|
||||
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,
|
||||
}]
|
Loading…
Reference in New Issue