_ Git - youtube-dl/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 TeamFourIE(InfoExtractor):
  85     _VALID_URL = r'https?://(?:www\.)?teamfourstar\.com/video/(?P<id>[a-z0-9\-]+)/?'
  86     _TEST = {
  87         'url': 'http://teamfourstar.com/video/a-moment-with-tfs-episode-4/',
  88         'info_dict': {
  89             'id': 'TeamFourStar-5292a02f20bfa',
  90             'ext': 'mp4',
  91             'upload_date': '20130401',
  92             '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',
  93             'title': 'A Moment With TFS Episode 4',
  94         }
  95     }
  96
  97     def _real_extract(self, url):
  98         display_id = self._match_id(url)
  99         webpage = self._download_webpage(url, display_id)
 100
 101         playerdata_url = self._search_regex(
 102             r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
 103             webpage, 'player data URL')
 104
 105         video_title = self._html_search_regex(
 106             r'<div class="heroheadingtitle">(?P<title>.+?)</div>',
 107             webpage, 'title')
 108         video_date = unified_strdate(self._html_search_regex(
 109             r'<div class="heroheadingdate">(?P<date>.+?)</div>',
 110             webpage, 'date', fatal=False))
 111         video_description = self._html_search_regex(
 112             r'(?s)<div class="postcontent">(?P<description>.+?)</div>',
 113             webpage, 'description', fatal=False)
 114         video_thumbnail = self._og_search_thumbnail(webpage)
 115
 116         return {
 117             '_type': 'url_transparent',
 118             'display_id': display_id,
 119             'title': video_title,
 120             'description': video_description,
 121             'upload_date': video_date,
 122             'thumbnail': video_thumbnail,
 123             'url': playerdata_url,
 124         }