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\d?\.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
  24         playerdata = self._download_webpage(
  25             'http://player.screenwavemedia.com/play/player.php?id=%s' % video_id,
  26             video_id, 'Downloading player webpage')
  27
  28         vidtitle = self._search_regex(
  29             r'\'vidtitle\'\s*:\s*"([^"]+)"', playerdata, 'vidtitle').replace('\\/', '/')
  30         vidurl = self._search_regex(
  31             r'\'vidurl\'\s*:\s*"([^"]+)"', playerdata, 'vidurl').replace('\\/', '/')
  32
  33         videolist_url = None
  34
  35         mobj = re.search(r"'videoserver'\s*:\s*'(?P<videoserver>[^']+)'", playerdata)
  36         if mobj:
  37             videoserver = mobj.group('videoserver')
  38             mobj = re.search(r'\'vidid\'\s*:\s*"(?P<vidid>[^\']+)"', playerdata)
  39             vidid = mobj.group('vidid') if mobj else video_id
  40             videolist_url = 'http://%s/vod/smil:%s.smil/jwplayer.smil' % (videoserver, vidid)
  41         else:
  42             mobj = re.search(r"file\s*:\s*'(?P<smil>http.+?/jwplayer\.smil)'", playerdata)
  43             if mobj:
  44                 videolist_url = mobj.group('smil')
  45
  46         if videolist_url:
  47             videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML')
  48             formats = []
  49             baseurl = vidurl[:vidurl.rfind('/') + 1]
  50             for video in videolist.findall('.//video'):
  51                 src = video.get('src')
  52                 if not src:
  53                     continue
  54                 file_ = src.partition(':')[-1]
  55                 width = int_or_none(video.get('width'))
  56                 height = int_or_none(video.get('height'))
  57                 bitrate = int_or_none(video.get('system-bitrate'), scale=1000)
  58                 format = {
  59                     'url': baseurl + file_,
  60                     'format_id': src.rpartition('.')[0].rpartition('_')[-1],
  61                 }
  62                 if width or height:
  63                     format.update({
  64                         'tbr': bitrate,
  65                         'width': width,
  66                         'height': height,
  67                     })
  68                 else:
  69                     format.update({
  70                         'abr': bitrate,
  71                         'vcodec': 'none',
  72                     })
  73                 formats.append(format)
  74         else:
  75             formats = [{
  76                 'url': vidurl,
  77             }]
  78         self._sort_formats(formats)
  79
  80         return {
  81             'id': video_id,
  82             'title': vidtitle,
  83             'formats': formats,
  84         }
  85
  86
  87 class TeamFourIE(InfoExtractor):
  88     _VALID_URL = r'https?://(?:www\.)?teamfourstar\.com/video/(?P<id>[a-z0-9\-]+)/?'
  89     _TEST = {
  90         'url': 'http://teamfourstar.com/video/a-moment-with-tfs-episode-4/',
  91         'info_dict': {
  92             'id': 'TeamFourStar-5292a02f20bfa',
  93             'ext': 'mp4',
  94             'upload_date': '20130401',
  95             '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',
  96             'title': 'A Moment With TFS Episode 4',
  97         }
  98     }
  99
 100     def _real_extract(self, url):
 101         display_id = self._match_id(url)
 102         webpage = self._download_webpage(url, display_id)
 103
 104         playerdata_url = self._search_regex(
 105             r'src="(http://player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
 106             webpage, 'player data URL')
 107
 108         video_title = self._html_search_regex(
 109             r'<div class="heroheadingtitle">(?P<title>.+?)</div>',
 110             webpage, 'title')
 111         video_date = unified_strdate(self._html_search_regex(
 112             r'<div class="heroheadingdate">(?P<date>.+?)</div>',
 113             webpage, 'date', fatal=False))
 114         video_description = self._html_search_regex(
 115             r'(?s)<div class="postcontent">(?P<description>.+?)</div>',
 116             webpage, 'description', fatal=False)
 117         video_thumbnail = self._og_search_thumbnail(webpage)
 118
 119         return {
 120             '_type': 'url_transparent',
 121             'display_id': display_id,
 122             'title': video_title,
 123             'description': video_description,
 124             'upload_date': video_date,
 125             'thumbnail': video_thumbnail,
 126             'url': playerdata_url,
 127         }