_ 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     ExtractorError
  11 )
  12 from .bliptv import BlipTVIE
  13
  14
  15 class ScreenwaveMediaIE(InfoExtractor):
  16     _VALID_URL = r'http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?P<id>.+)'
  17
  18     _TESTS = [{
  19         'url': 'http://player.screenwavemedia.com/play/play.php?playerdiv=videoarea&companiondiv=squareAd&id=Cinemassacre-19911',
  20         'only_matching': True,
  21     }]
  22
  23     def _real_extract(self, url):
  24         video_id = self._match_id(url)
  25         playerdata = self._download_webpage(url, video_id, 'Downloading player webpage')
  26
  27         vidtitle = self._search_regex(
  28             r'\'vidtitle\'\s*:\s*"([^"]+)"', playerdata, 'vidtitle').replace('\\/', '/')
  29         vidurl = self._search_regex(
  30             r'\'vidurl\'\s*:\s*"([^"]+)"', playerdata, 'vidurl').replace('\\/', '/')
  31
  32         videolist_url = None
  33
  34         mobj = re.search(r"'videoserver'\s*:\s*'(?P<videoserver>[^']+)'", playerdata)
  35         if mobj:
  36             videoserver = mobj.group('videoserver')
  37             mobj = re.search(r'\'vidid\'\s*:\s*"(?P<vidid>[^\']+)"', playerdata)
  38             vidid = mobj.group('vidid') if mobj else video_id
  39             videolist_url = 'http://%s/vod/smil:%s.smil/jwplayer.smil' % (videoserver, vidid)
  40         else:
  41             mobj = re.search(r"file\s*:\s*'(?P<smil>http.+?/jwplayer\.smil)'", playerdata)
  42             if mobj:
  43                 videolist_url = mobj.group('smil')
  44
  45         if videolist_url:
  46             videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML')
  47             formats = []
  48             baseurl = vidurl[:vidurl.rfind('/') + 1]
  49             for video in videolist.findall('.//video'):
  50                 src = video.get('src')
  51                 if not src:
  52                     continue
  53                 file_ = src.partition(':')[-1]
  54                 width = int_or_none(video.get('width'))
  55                 height = int_or_none(video.get('height'))
  56                 bitrate = int_or_none(video.get('system-bitrate'), scale=1000)
  57                 format = {
  58                     'url': baseurl + file_,
  59                     'format_id': src.rpartition('.')[0].rpartition('_')[-1],
  60                 }
  61                 if width or height:
  62                     format.update({
  63                         'tbr': bitrate,
  64                         'width': width,
  65                         'height': height,
  66                     })
  67                 else:
  68                     format.update({
  69                         'abr': bitrate,
  70                         'vcodec': 'none',
  71                     })
  72                 formats.append(format)
  73         else:
  74             formats = [{
  75                 'url': vidurl,
  76             }]
  77         self._sort_formats(formats)
  78
  79         return {
  80             'id': video_id,
  81             'title': vidtitle,
  82             'formats': formats,
  83         }
  84
  85
  86 class CinemassacreIE(InfoExtractor):
  87     _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>[^?#/]+)'
  88     _TESTS = [
  89         {
  90             'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
  91             'md5': 'fde81fbafaee331785f58cd6c0d46190',
  92             'info_dict': {
  93                 'id': 'Cinemassacre-19911',
  94                 'ext': 'mp4',
  95                 'upload_date': '20121110',
  96                 'title': '“Angry Video Game Nerd: The Movie” – Trailer',
  97                 'description': 'md5:fb87405fcb42a331742a0dce2708560b',
  98             },
  99         },
 100         {
 101             'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
 102             'md5': 'd72f10cd39eac4215048f62ab477a511',
 103             'info_dict': {
 104                 'id': 'Cinemassacre-521be8ef82b16',
 105                 'ext': 'mp4',
 106                 'upload_date': '20131002',
 107                 'title': 'The Mummy’s Hand (1940)',
 108             },
 109         },
 110         {
 111             'url': 'http://cinemassacre.com/2006/12/07/chronologically-confused-about-bad-movie-and-video-game-sequel-titles/',
 112             'md5': 'ca9b3c8dd5a66f9375daeb5135f5a3de',
 113             'info_dict': {
 114                 'id': '4065369',
 115                 'ext': 'flv',
 116                 'title': 'AVGN: Chronologically Confused about Bad Movie and Video Game Sequel Titles',
 117                 'upload_date': '20061207',
 118                 'uploader': 'cinemassacre',
 119                 'uploader_id': '250778',
 120                 'timestamp': 1283233867,
 121                 'description': 'md5:0a108c78d130676b207d0f6d029ecffd',
 122             }
 123         }
 124     ]
 125
 126     def _real_extract(self, url):
 127         mobj = re.match(self._VALID_URL, url)
 128         display_id = mobj.group('display_id')
 129         video_date = mobj.group('date_y') + mobj.group('date_m') + mobj.group('date_d')
 130
 131         webpage = self._download_webpage(url, display_id)
 132
 133         playerdata_url = self._search_regex(
 134             r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
 135             webpage, 'player data URL', default=None)
 136         if not playerdata_url:
 137             playerdata_url = BlipTVIE._extract_url(webpage)
 138         if not playerdata_url:
 139             raise ExtractorError('Unable to find player data')
 140
 141         video_title = self._html_search_regex(
 142             r'<title>(?P<title>.+?)\|', webpage, 'title')
 143         video_description = self._html_search_regex(
 144             r'<div class="entry-content">(?P<description>.+?)</div>',
 145             webpage, 'description', flags=re.DOTALL, fatal=False)
 146         video_thumbnail = self._og_search_thumbnail(webpage)
 147
 148         return {
 149             '_type': 'url_transparent',
 150             'display_id': display_id,
 151             'title': video_title,
 152             'description': video_description,
 153             'upload_date': video_date,
 154             'thumbnail': video_thumbnail,
 155             'url': playerdata_url,
 156         }
 157
 158
 159 class TeamFourIE(InfoExtractor):
 160     _VALID_URL = r'https?://(?:www\.)?teamfourstar\.com/video/(?P<id>[a-z0-9\-]+)/?'
 161     _TEST = {
 162         'url': 'http://teamfourstar.com/video/a-moment-with-tfs-episode-4/',
 163         'info_dict': {
 164             'id': 'TeamFourStar-5292a02f20bfa',
 165             'ext': 'mp4',
 166             'upload_date': '20130401',
 167             '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',
 168             'title': 'A Moment With TFS Episode 4',
 169         }
 170     }
 171
 172     def _real_extract(self, url):
 173         display_id = self._match_id(url)
 174         webpage = self._download_webpage(url, display_id)
 175
 176         playerdata_url = self._search_regex(
 177             r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
 178             webpage, 'player data URL')
 179
 180         video_title = self._html_search_regex(
 181             r'<div class="heroheadingtitle">(?P<title>.+?)</div>',
 182             webpage, 'title')
 183         video_date = unified_strdate(self._html_search_regex(
 184             r'<div class="heroheadingdate">(?P<date>.+?)</div>',
 185             webpage, 'date', fatal=False))
 186         video_description = self._html_search_regex(
 187             r'(?s)<div class="postcontent">(?P<description>.+?)</div>',
 188             webpage, 'description', fatal=False)
 189         video_thumbnail = self._og_search_thumbnail(webpage)
 190
 191         return {
 192             '_type': 'url_transparent',
 193             'display_id': display_id,
 194             'title': video_title,
 195             'description': video_description,
 196             'upload_date': video_date,
 197             'thumbnail': video_thumbnail,
 198             'url': playerdata_url,
 199         }