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     js_to_json,
  11 )
  12
  13
  14 class ScreenwaveMediaIE(InfoExtractor):
  15     _VALID_URL = r'(?:https?:)?//player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?.*\bid=(?P<id>[A-Za-z0-9-]+)'
  16     EMBED_PATTERN = r'src=(["\'])(?P<url>(?:https?:)?//player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?.*\bid=.+?)\1'
  17     _TESTS = [{
  18         'url': 'http://player.screenwavemedia.com/play/play.php?playerdiv=videoarea&companiondiv=squareAd&id=Cinemassacre-19911',
  19         'only_matching': True,
  20     }]
  21
  22     def _real_extract(self, url):
  23         video_id = self._match_id(url)
  24
  25         playerdata = self._download_webpage(
  26             'http://player.screenwavemedia.com/player.php?id=%s' % video_id,
  27             video_id, 'Downloading player webpage')
  28
  29         vidtitle = self._search_regex(
  30             r'\'vidtitle\'\s*:\s*"([^"]+)"', playerdata, 'vidtitle').replace('\\/', '/')
  31
  32         playerconfig = self._download_webpage(
  33             'http://player.screenwavemedia.com/player.js',
  34             video_id, 'Downloading playerconfig webpage')
  35
  36         videoserver = self._search_regex(r'SWMServer\s*=\s*"([\d\.]+)"', playerdata, 'videoserver')
  37
  38         sources = self._parse_json(
  39             js_to_json(
  40                 re.sub(
  41                     r'(?s)/\*.*?\*/', '',
  42                     self._search_regex(
  43                         r'sources\s*:\s*(\[[^\]]+?\])', playerconfig,
  44                         'sources',
  45                     ).replace(
  46                         "' + thisObj.options.videoserver + '",
  47                         videoserver
  48                     ).replace(
  49                         "' + playerVidId + '",
  50                         video_id
  51                     )
  52                 )
  53             ),
  54             video_id, fatal=False
  55         )
  56
  57         # Fallback to hardcoded sources if JS changes again
  58         if not sources:
  59             self.report_warning('Falling back to a hardcoded list of streams')
  60             sources = [{
  61                 'file': 'http://%s/vod/%s_%s.mp4' % (videoserver, video_id, format_id),
  62                 'type': 'mp4',
  63                 'label': format_label,
  64             } for format_id, format_label in (
  65                 ('low', '144p Low'), ('med', '160p Med'), ('high', '360p High'), ('hd1', '720p HD1'))]
  66             sources.append({
  67                 'file': 'http://%s/vod/smil:%s.smil/playlist.m3u8' % (videoserver, video_id),
  68                 'type': 'hls',
  69             })
  70
  71         formats = []
  72         for source in sources:
  73             file_ = source.get('file')
  74             if not file_:
  75                 continue
  76             if source.get('type') == 'hls':
  77                 formats.extend(self._extract_m3u8_formats(file_, video_id, ext='mp4'))
  78             else:
  79                 format_id = self._search_regex(
  80                     r'_(.+?)\.[^.]+$', file_, 'format id', default=None)
  81                 if not self._is_valid_url(file_, video_id, format_id or 'video'):
  82                     continue
  83                 format_label = source.get('label')
  84                 height = int_or_none(self._search_regex(
  85                     r'^(\d+)[pP]', format_label, 'height', default=None))
  86                 formats.append({
  87                     'url': file_,
  88                     'format_id': format_id,
  89                     'format': format_label,
  90                     'ext': source.get('type'),
  91                     'height': height,
  92                 })
  93         self._sort_formats(formats, field_preference=('height', 'width', 'tbr', 'format_id'))
  94
  95         return {
  96             'id': video_id,
  97             'title': vidtitle,
  98             'formats': formats,
  99         }
 100
 101
 102 class TeamFourIE(InfoExtractor):
 103     _VALID_URL = r'https?://(?:www\.)?teamfourstar\.com/video/(?P<id>[a-z0-9\-]+)/?'
 104     _TEST = {
 105         'url': 'http://teamfourstar.com/video/a-moment-with-tfs-episode-4/',
 106         'info_dict': {
 107             'id': 'TeamFourStar-5292a02f20bfa',
 108             'ext': 'mp4',
 109             'upload_date': '20130401',
 110             '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',
 111             'title': 'A Moment With TFS Episode 4',
 112         },
 113         'params': {
 114             # m3u8 download
 115             'skip_download': True,
 116         },
 117     }
 118
 119     def _real_extract(self, url):
 120         display_id = self._match_id(url)
 121         webpage = self._download_webpage(url, display_id)
 122
 123         playerdata_url = self._search_regex(
 124             r'src="(http://player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
 125             webpage, 'player data URL')
 126
 127         video_title = self._html_search_regex(
 128             r'<div class="heroheadingtitle">(?P<title>.+?)</div>',
 129             webpage, 'title')
 130         video_date = unified_strdate(self._html_search_regex(
 131             r'<div class="heroheadingdate">(?P<date>.+?)</div>',
 132             webpage, 'date', fatal=False))
 133         video_description = self._html_search_regex(
 134             r'(?s)<div class="postcontent">(?P<description>.+?)</div>',
 135             webpage, 'description', fatal=False)
 136         video_thumbnail = self._og_search_thumbnail(webpage)
 137
 138         return {
 139             '_type': 'url_transparent',
 140             'display_id': display_id,
 141             'title': video_title,
 142             'description': video_description,
 143             'upload_date': video_date,
 144             'thumbnail': video_thumbnail,
 145             'url': playerdata_url,
 146         }