_ 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     js_to_json,
  11 )
  12
  13
  14 class ScreenwaveMediaIE(InfoExtractor):
  15     _VALID_URL = r'http://player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?[^"]*\bid=(?P<id>.+)'
  16
  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"\[ipaddress\]\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
  55         )
  56
  57         formats = []
  58         for source in sources:
  59             if source['type'] == 'hls':
  60                 formats.extend(self._extract_m3u8_formats(source['file'], video_id))
  61             else:
  62                 format_label = source.get('label')
  63                 height = int_or_none(self._search_regex(
  64                     r'^(\d+)[pP]', format_label, 'height', default=None))
  65                 formats.append({
  66                     'url': source['file'],
  67                     'format': format_label,
  68                     'ext': source.get('type'),
  69                     'height': height,
  70                 })
  71         self._sort_formats(formats)
  72
  73         return {
  74             'id': video_id,
  75             'title': vidtitle,
  76             'formats': formats,
  77         }
  78
  79
  80 class TeamFourIE(InfoExtractor):
  81     _VALID_URL = r'https?://(?:www\.)?teamfourstar\.com/video/(?P<id>[a-z0-9\-]+)/?'
  82     _TEST = {
  83         'url': 'http://teamfourstar.com/video/a-moment-with-tfs-episode-4/',
  84         'info_dict': {
  85             'id': 'TeamFourStar-5292a02f20bfa',
  86             'ext': 'mp4',
  87             'upload_date': '20130401',
  88             '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',
  89             'title': 'A Moment With TFS Episode 4',
  90         }
  91     }
  92
  93     def _real_extract(self, url):
  94         display_id = self._match_id(url)
  95         webpage = self._download_webpage(url, display_id)
  96
  97         playerdata_url = self._search_regex(
  98             r'src="(http://player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
  99             webpage, 'player data URL')
 100
 101         video_title = self._html_search_regex(
 102             r'<div class="heroheadingtitle">(?P<title>.+?)</div>',
 103             webpage, 'title')
 104         video_date = unified_strdate(self._html_search_regex(
 105             r'<div class="heroheadingdate">(?P<date>.+?)</div>',
 106             webpage, 'date', fatal=False))
 107         video_description = self._html_search_regex(
 108             r'(?s)<div class="postcontent">(?P<description>.+?)</div>',
 109             webpage, 'description', fatal=False)
 110         video_thumbnail = self._og_search_thumbnail(webpage)
 111
 112         return {
 113             '_type': 'url_transparent',
 114             'display_id': display_id,
 115             'title': video_title,
 116             'description': video_description,
 117             'upload_date': video_date,
 118             'thumbnail': video_thumbnail,
 119             'url': playerdata_url,
 120         }