yt_dlp/extractor/joj.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_str
   3 from ..utils import (
   4     format_field,
   5     int_or_none,
   6     js_to_json,
   7     try_get,
   8 )
   9
  10
  11 class JojIE(InfoExtractor):
  12     _VALID_URL = r'''(?x)
  13                     (?:
  14                         joj:|
  15                         https?://media\.joj\.sk/embed/
  16                     )
  17                     (?P<id>[^/?#^]+)
  18                 '''
  19     _EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//media\.joj\.sk/embed/(?:(?!\1).)+)\1']
  20     _TESTS = [{
  21         'url': 'https://media.joj.sk/embed/a388ec4c-6019-4a4a-9312-b1bee194e932',
  22         'info_dict': {
  23             'id': 'a388ec4c-6019-4a4a-9312-b1bee194e932',
  24             'ext': 'mp4',
  25             'title': 'NOVÉ BÝVANIE',
  26             'thumbnail': r're:^https?://.*?$',
  27             'duration': 3118,
  28         }
  29     }, {
  30         'url': 'https://media.joj.sk/embed/CSM0Na0l0p1',
  31         'info_dict': {
  32             'id': 'CSM0Na0l0p1',
  33             'ext': 'mp4',
  34             'height': 576,
  35             'title': 'Extrémne rodiny 2 - POKRAČOVANIE (2012/04/09 21:30:00)',
  36             'duration': 3937,
  37             'thumbnail': r're:^https?://.*?$',
  38         }
  39     }, {
  40         'url': 'https://media.joj.sk/embed/9i1cxv',
  41         'only_matching': True,
  42     }, {
  43         'url': 'joj:a388ec4c-6019-4a4a-9312-b1bee194e932',
  44         'only_matching': True,
  45     }, {
  46         'url': 'joj:9i1cxv',
  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             'https://media.joj.sk/embed/%s' % video_id, video_id)
  55
  56         title = (self._search_json(r'videoTitle\s*:', webpage, 'title', video_id,
  57                                    contains_pattern=r'["\'].+["\']', default=None)
  58                  or self._html_extract_title(webpage, default=None)
  59                  or self._og_search_title(webpage))
  60
  61         bitrates = self._parse_json(
  62             self._search_regex(
  63                 r'(?s)(?:src|bitrates)\s*=\s*({.+?});', webpage, 'bitrates',
  64                 default='{}'),
  65             video_id, transform_source=js_to_json, fatal=False)
  66
  67         formats = []
  68         for format_url in try_get(bitrates, lambda x: x['mp4'], list) or []:
  69             if isinstance(format_url, compat_str):
  70                 height = self._search_regex(
  71                     r'(\d+)[pP]|(pal)\.', format_url, 'height', default=None)
  72                 if height == 'pal':
  73                     height = 576
  74                 formats.append({
  75                     'url': format_url,
  76                     'format_id': format_field(height, None, '%sp'),
  77                     'height': int_or_none(height),
  78                 })
  79         if not formats:
  80             playlist = self._download_xml(
  81                 'https://media.joj.sk/services/Video.php?clip=%s' % video_id,
  82                 video_id)
  83             for file_el in playlist.findall('./files/file'):
  84                 path = file_el.get('path')
  85                 if not path:
  86                     continue
  87                 format_id = file_el.get('id') or file_el.get('label')
  88                 formats.append({
  89                     'url': 'http://n16.joj.sk/storage/%s' % path.replace(
  90                         'dat/', '', 1),
  91                     'format_id': format_id,
  92                     'height': int_or_none(self._search_regex(
  93                         r'(\d+)[pP]', format_id or path, 'height',
  94                         default=None)),
  95                 })
  96
  97         thumbnail = self._og_search_thumbnail(webpage)
  98
  99         duration = int_or_none(self._search_regex(
 100             r'videoDuration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
 101
 102         return {
 103             'id': video_id,
 104             'title': title,
 105             'thumbnail': thumbnail,
 106             'duration': duration,
 107             'formats': formats,
 108         }