Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/screenwavemedia.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     int_or_none,
   9     unified_strdate,
  10 )
  11
  12
  13 class ScreenwaveMediaIE(InfoExtractor):
  14     _VALID_URL = r'http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?P<id>.+)'
  15
  16     _TESTS = [{
  17         'url': 'http://player.screenwavemedia.com/play/play.php?playerdiv=videoarea&companiondiv=squareAd&id=Cinemassacre-19911',
  18         'only_matching': True,
  19     }]
  20
  21     def _real_extract(self, url):
  22         video_id = self._match_id(url)
  23         playerdata = self._download_webpage(url, video_id, 'Downloading player webpage')
  24
  25         vidtitle = self._search_regex(
  26             r'\'vidtitle\'\s*:\s*"([^"]+)"', playerdata, 'vidtitle').replace('\\/', '/')
  27         vidurl = self._search_regex(
  28             r'\'vidurl\'\s*:\s*"([^"]+)"', playerdata, 'vidurl').replace('\\/', '/')
  29
  30         videolist_url = None
  31
  32         mobj = re.search(r"'videoserver'\s*:\s*'(?P<videoserver>[^']+)'", playerdata)
  33         if mobj:
  34             videoserver = mobj.group('videoserver')
  35             mobj = re.search(r'\'vidid\'\s*:\s*"(?P<vidid>[^\']+)"', playerdata)
  36             vidid = mobj.group('vidid') if mobj else video_id
  37             videolist_url = 'http://%s/vod/smil:%s.smil/jwplayer.smil' % (videoserver, vidid)
  38         else:
  39             mobj = re.search(r"file\s*:\s*'(?P<smil>http.+?/jwplayer\.smil)'", playerdata)
  40             if mobj:
  41                 videolist_url = mobj.group('smil')
  42
  43         if videolist_url:
  44             videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML')
  45             formats = []
  46             baseurl = vidurl[:vidurl.rfind('/') + 1]
  47             for video in videolist.findall('.//video'):
  48                 src = video.get('src')
  49                 if not src:
  50                     continue
  51                 file_ = src.partition(':')[-1]
  52                 width = int_or_none(video.get('width'))
  53                 height = int_or_none(video.get('height'))
  54                 bitrate = int_or_none(video.get('system-bitrate'), scale=1000)
  55                 format = {
  56                     'url': baseurl + file_,
  57                     'format_id': src.rpartition('.')[0].rpartition('_')[-1],
  58                 }
  59                 if width or height:
  60                     format.update({
  61                         'tbr': bitrate,
  62                         'width': width,
  63                         'height': height,
  64                     })
  65                 else:
  66                     format.update({
  67                         'abr': bitrate,
  68                         'vcodec': 'none',
  69                     })
  70                 formats.append(format)
  71         else:
  72             formats = [{
  73                 'url': vidurl,
  74             }]
  75         self._sort_formats(formats)
  76
  77         return {
  78             'id': video_id,
  79             'title': vidtitle,
  80             'formats': formats,
  81         }
  82
  83
  84 class CinemassacreIE(InfoExtractor):
  85     _VALID_URL = 'https?://(?:www\.)?cinemassacre\.com/(?P<date_y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)'
  86     _TESTS = [
  87         {
  88             'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
  89             'md5': 'fde81fbafaee331785f58cd6c0d46190',
  90             'info_dict': {
  91                 'id': 'Cinemassacre-19911',
  92                 'ext': 'mp4',
  93                 'upload_date': '20121110',
  94                 'title': '“Angry Video Game Nerd: The Movie” – Trailer',
  95                 'description': 'md5:fb87405fcb42a331742a0dce2708560b',
  96             },
  97         },
  98         {
  99             'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
 100             'md5': 'd72f10cd39eac4215048f62ab477a511',
 101             'info_dict': {
 102                 'id': 'Cinemassacre-521be8ef82b16',
 103                 'ext': 'mp4',
 104                 'upload_date': '20131002',
 105                 'title': 'The Mummy’s Hand (1940)',
 106             },
 107         }
 108     ]
 109
 110     def _real_extract(self, url):
 111         mobj = re.match(self._VALID_URL, url)
 112         display_id = mobj.group('display_id')
 113         video_date = mobj.group('date_y') + mobj.group('date_m') + mobj.group('date_d')
 114
 115         webpage = self._download_webpage(url, display_id)
 116
 117         playerdata_url = self._search_regex(
 118             r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
 119             webpage, 'player data URL')
 120         video_title = self._html_search_regex(
 121             r'<title>(?P<title>.+?)\|', webpage, 'title')
 122         video_description = self._html_search_regex(
 123             r'<div class="entry-content">(?P<description>.+?)</div>',
 124             webpage, 'description', flags=re.DOTALL, fatal=False)
 125         video_thumbnail = self._og_search_thumbnail(webpage)
 126
 127         return {
 128             '_type': 'url_transparent',
 129             'display_id': display_id,
 130             'title': video_title,
 131             'description': video_description,
 132             'upload_date': video_date,
 133             'thumbnail': video_thumbnail,
 134             'url': playerdata_url,
 135         }
 136
 137
 138 class TeamFourIE(InfoExtractor):
 139     _VALID_URL = r'https?://(?:www\.)?teamfourstar\.com/video/(?P<id>[a-z0-9\-]+)/?'
 140     _TEST = {
 141         'url': 'http://teamfourstar.com/video/a-moment-with-tfs-episode-4/',
 142         'info_dict': {
 143             'id': 'TeamFourStar-5292a02f20bfa',
 144             'ext': 'mp4',
 145             'upload_date': '20130401',
 146             'description': 'Check out this and more on our website: http://teamfourstar.com\nTFS Store: http://sharkrobot.com/team-four-star\nFollow on Twitter: http://twitter.com/teamfourstar\nLike on FB: http://facebook.com/teamfourstar',
 147             'title': 'A Moment With TFS Episode 4',
 148         }
 149     }
 150
 151     def _real_extract(self, url):
 152         display_id = self._match_id(url)
 153         webpage = self._download_webpage(url, display_id)
 154
 155         playerdata_url = self._search_regex(
 156             r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
 157             webpage, 'player data URL')
 158
 159         video_title = self._html_search_regex(
 160             r'<div class="heroheadingtitle">(?P<title>.+?)</div>',
 161             webpage, 'title')
 162         video_date = unified_strdate(self._html_search_regex(
 163             r'<div class="heroheadingdate">(?P<date>.+?)</div>',
 164             webpage, 'date', fatal=False))
 165         video_description = self._html_search_regex(
 166             r'(?s)<div class="postcontent">(?P<description>.+?)</div>',
 167             webpage, 'description', fatal=False)
 168         video_thumbnail = self._og_search_thumbnail(webpage)
 169
 170         return {
 171             '_type': 'url_transparent',
 172             'display_id': display_id,
 173             'title': video_title,
 174             'description': video_description,
 175             'upload_date': video_date,
 176             'thumbnail': video_thumbnail,
 177             'url': playerdata_url,
 178         }