yt_dlp/extractor/zapiks.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     int_or_none,
   6     parse_duration,
   7     parse_iso8601,
   8     xpath_text,
   9     xpath_with_ns,
  10 )
  11
  12
  13 class ZapiksIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?zapiks\.(?:fr|com)/(?:(?:[a-z]{2}/)?(?P<display_id>.+?)\.html|index\.php\?.*\bmedia_id=(?P<id>\d+))'
  15     _EMBED_REGEX = [r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"']
  16     _TESTS = [
  17         {
  18             'url': 'http://www.zapiks.fr/ep2s3-bon-appetit-eh-be-viva.html',
  19             'md5': 'aeb3c473b2d564b2d46d664d28d5f050',
  20             'info_dict': {
  21                 'id': '80798',
  22                 'ext': 'mp4',
  23                 'title': 'EP2S3 - Bon Appétit - Eh bé viva les pyrénées con!',
  24                 'description': 'md5:7054d6f6f620c6519be1fe710d4da847',
  25                 'thumbnail': r're:^https?://.*\.jpg$',
  26                 'duration': 528,
  27                 'timestamp': 1359044972,
  28                 'upload_date': '20130124',
  29                 'view_count': int,
  30             },
  31         },
  32         {
  33             'url': 'http://www.zapiks.com/ep3s5-bon-appetit-baqueira-m-1.html',
  34             'only_matching': True,
  35         },
  36         {
  37             'url': 'http://www.zapiks.com/nl/ep3s5-bon-appetit-baqueira-m-1.html',
  38             'only_matching': True,
  39         },
  40         {
  41             'url': 'http://www.zapiks.fr/index.php?action=playerIframe&amp;media_id=118046&amp;width=640&amp;height=360&amp;autoStart=false&amp;language=fr',
  42             'only_matching': True,
  43         },
  44     ]
  45
  46     def _real_extract(self, url):
  47         mobj = self._match_valid_url(url)
  48         video_id = mobj.group('id')
  49         display_id = mobj.group('display_id') or video_id
  50
  51         webpage = self._download_webpage(url, display_id)
  52
  53         if not video_id:
  54             video_id = self._search_regex(
  55                 r'data-media-id="(\d+)"', webpage, 'video id')
  56
  57         playlist = self._download_xml(
  58             'http://www.zapiks.fr/view/index.php?action=playlist&media_id=%s&lang=en' % video_id,
  59             display_id)
  60
  61         NS_MAP = {
  62             'jwplayer': 'http://rss.jwpcdn.com/'
  63         }
  64
  65         def ns(path):
  66             return xpath_with_ns(path, NS_MAP)
  67
  68         item = playlist.find('./channel/item')
  69
  70         title = xpath_text(item, 'title', 'title') or self._og_search_title(webpage)
  71         description = self._og_search_description(webpage, default=None)
  72         thumbnail = xpath_text(
  73             item, ns('./jwplayer:image'), 'thumbnail') or self._og_search_thumbnail(webpage, default=None)
  74         duration = parse_duration(self._html_search_meta(
  75             'duration', webpage, 'duration', default=None))
  76         timestamp = parse_iso8601(self._html_search_meta(
  77             'uploadDate', webpage, 'upload date', default=None), ' ')
  78
  79         view_count = int_or_none(self._search_regex(
  80             r'UserPlays:(\d+)', webpage, 'view count', default=None))
  81         comment_count = int_or_none(self._search_regex(
  82             r'UserComments:(\d+)', webpage, 'comment count', default=None))
  83
  84         formats = []
  85         for source in item.findall(ns('./jwplayer:source')):
  86             format_id = source.attrib['label']
  87             f = {
  88                 'url': source.attrib['file'],
  89                 'format_id': format_id,
  90             }
  91             m = re.search(r'^(?P<height>\d+)[pP]', format_id)
  92             if m:
  93                 f['height'] = int(m.group('height'))
  94             formats.append(f)
  95
  96         return {
  97             'id': video_id,
  98             'title': title,
  99             'description': description,
 100             'thumbnail': thumbnail,
 101             'duration': duration,
 102             'timestamp': timestamp,
 103             'view_count': view_count,
 104             'comment_count': comment_count,
 105             'formats': formats,
 106         }