youtube_dl/extractor/tvp.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class TVPIE(InfoExtractor):
  10     IE_NAME = 'tvp'
  11     IE_DESC = 'Telewizja Polska'
  12     _VALID_URL = r'https?://[^/]+\.tvp\.(?:pl|info)/(?:(?!\d+/)[^/]+/)*(?P<id>\d+)'
  13
  14     _TESTS = [{
  15         'url': 'http://vod.tvp.pl/194536/i-seria-odc-13',
  16         'md5': '8aa518c15e5cc32dfe8db400dc921fbb',
  17         'info_dict': {
  18             'id': '194536',
  19             'ext': 'mp4',
  20             'title': 'Czas honoru, I seria – odc. 13',
  21         },
  22     }, {
  23         'url': 'http://www.tvp.pl/there-can-be-anything-so-i-shortened-it/17916176',
  24         'md5': 'c3b15ed1af288131115ff17a17c19dda',
  25         'info_dict': {
  26             'id': '17916176',
  27             'ext': 'mp4',
  28             'title': 'TVP Gorzów pokaże filmy studentów z podroży dookoła świata',
  29         },
  30     }, {
  31         'url': 'http://vod.tvp.pl/seriale/obyczajowe/na-sygnale/sezon-2-27-/odc-39/17834272',
  32         'only_matching': True,
  33     }, {
  34         'url': 'http://wiadomosci.tvp.pl/25169746/24052016-1200',
  35         'only_matching': True,
  36     }, {
  37         'url': 'http://krakow.tvp.pl/25511623/25lecie-mck-wyjatkowe-miejsce-na-mapie-krakowa',
  38         'only_matching': True,
  39     }, {
  40         'url': 'http://teleexpress.tvp.pl/25522307/wierni-wzieli-udzial-w-procesjach',
  41         'only_matching': True,
  42     }, {
  43         'url': 'http://sport.tvp.pl/25522165/krychowiak-uspokaja-w-sprawie-kontuzji-dwa-tygodnie-to-maksimum',
  44         'only_matching': True,
  45     }, {
  46         'url': 'http://www.tvp.info/25511919/trwa-rewolucja-wladza-zdecydowala-sie-na-pogwalcenie-konstytucji',
  47         'only_matching': True,
  48     }]
  49
  50     def _real_extract(self, url):
  51         video_id = self._match_id(url)
  52
  53         webpage = self._download_webpage(
  54             'http://www.tvp.pl/sess/tvplayer.php?object_id=%s' % video_id, video_id)
  55
  56         title = self._search_regex(
  57             r'name\s*:\s*([\'"])Title\1\s*,\s*value\s*:\s*\1(?P<title>.+?)\1',
  58             webpage, 'title', group='title')
  59         series_title = self._search_regex(
  60             r'name\s*:\s*([\'"])SeriesTitle\1\s*,\s*value\s*:\s*\1(?P<series>.+?)\1',
  61             webpage, 'series', group='series', default=None)
  62         if series_title:
  63             title = '%s, %s' % (series_title, title)
  64
  65         thumbnail = self._search_regex(
  66             r"poster\s*:\s*'([^']+)'", webpage, 'thumbnail', default=None)
  67
  68         video_url = self._search_regex(
  69             r'0:{src:([\'"])(?P<url>.*?)\1', webpage, 'formats', group='url', default=None)
  70         if not video_url:
  71             video_url = self._download_json(
  72                 'http://www.tvp.pl/pub/stat/videofileinfo?video_id=%s' % video_id,
  73                 video_id)['video_url']
  74
  75         ext = video_url.rsplit('.', 1)[-1]
  76         if ext != 'ism/manifest':
  77             if '/' in ext:
  78                 ext = 'mp4'
  79             formats = [{
  80                 'format_id': 'direct',
  81                 'url': video_url,
  82                 'ext': ext,
  83             }]
  84         else:
  85             m3u8_url = re.sub('([^/]*)\.ism/manifest', r'\1.ism/\1.m3u8', video_url)
  86             formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
  87
  88         self._sort_formats(formats)
  89
  90         return {
  91             'id': video_id,
  92             'title': title,
  93             'thumbnail': thumbnail,
  94             'formats': formats,
  95         }
  96
  97
  98 class TVPSeriesIE(InfoExtractor):
  99     IE_NAME = 'tvp:series'
 100     _VALID_URL = r'https?://vod\.tvp\.pl/(?:[^/]+/){2}(?P<id>[^/]+)/?$'
 101
 102     _TESTS = [{
 103         'url': 'http://vod.tvp.pl/filmy-fabularne/filmy-za-darmo/ogniem-i-mieczem',
 104         'info_dict': {
 105             'title': 'Ogniem i mieczem',
 106             'id': '4278026',
 107         },
 108         'playlist_count': 4,
 109     }, {
 110         'url': 'http://vod.tvp.pl/audycje/podroze/boso-przez-swiat',
 111         'info_dict': {
 112             'title': 'Boso przez świat',
 113             'id': '9329207',
 114         },
 115         'playlist_count': 86,
 116     }]
 117
 118     def _real_extract(self, url):
 119         display_id = self._match_id(url)
 120         webpage = self._download_webpage(url, display_id, tries=5)
 121
 122         title = self._html_search_regex(
 123             r'(?s) id=[\'"]path[\'"]>(?:.*? / ){2}(.*?)</span>', webpage, 'series')
 124         playlist_id = self._search_regex(r'nodeId:\s*(\d+)', webpage, 'playlist id')
 125         playlist = self._download_webpage(
 126             'http://vod.tvp.pl/vod/seriesAjax?type=series&nodeId=%s&recommend'
 127             'edId=0&sort=&page=0&pageSize=10000' % playlist_id, display_id, tries=5,
 128             note='Downloading playlist')
 129
 130         videos_paths = re.findall(
 131             '(?s)class="shortTitle">.*?href="(/[^"]+)', playlist)
 132         entries = [
 133             self.url_result('http://vod.tvp.pl%s' % v_path, ie=TVPIE.ie_key())
 134             for v_path in videos_paths]
 135
 136         return {
 137             '_type': 'playlist',
 138             'id': playlist_id,
 139             'display_id': display_id,
 140             'title': title,
 141             'entries': entries,
 142         }