yt_dlp/extractor/medialaan.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     extract_attributes,
   8     int_or_none,
   9     mimetype2ext,
  10     parse_iso8601,
  11 )
  12
  13
  14 class MedialaanIE(InfoExtractor):
  15     _VALID_URL = r'''(?x)
  16                     https?://
  17                         (?:
  18                             (?:embed\.)?mychannels.video/embed/|
  19                             embed\.mychannels\.video/(?:s(?:dk|cript)/)?production/|
  20                             (?:www\.)?(?:
  21                                 (?:
  22                                     7sur7|
  23                                     demorgen|
  24                                     hln|
  25                                     joe|
  26                                     qmusic
  27                                 )\.be|
  28                                 (?:
  29                                     [abe]d|
  30                                     bndestem|
  31                                     destentor|
  32                                     gelderlander|
  33                                     pzc|
  34                                     tubantia|
  35                                     volkskrant
  36                                 )\.nl
  37                             )/video/(?:[^/]+/)*[^/?&#]+~p
  38                         )
  39                         (?P<id>\d+)
  40                     '''
  41     _TESTS = [{
  42         'url': 'https://www.bndestem.nl/video/de-terugkeer-van-ally-de-aap-en-wie-vertrekt-er-nog-bij-nac~p193993',
  43         'info_dict': {
  44             'id': '193993',
  45             'ext': 'mp4',
  46             'title': 'De terugkeer van Ally de Aap en wie vertrekt er nog bij NAC?',
  47             'timestamp': 1611663540,
  48             'upload_date': '20210126',
  49             'duration': 238,
  50         },
  51         'params': {
  52             'skip_download': True,
  53         },
  54     }, {
  55         'url': 'https://www.gelderlander.nl/video/kanalen/degelderlander~c320/series/snel-nieuws~s984/noodbevel-in-doetinchem-politie-stuurt-mensen-centrum-uit~p194093',
  56         'only_matching': True,
  57     }, {
  58         'url': 'https://embed.mychannels.video/sdk/production/193993?options=TFTFF_default',
  59         'only_matching': True,
  60     }, {
  61         'url': 'https://embed.mychannels.video/script/production/193993',
  62         'only_matching': True,
  63     }, {
  64         'url': 'https://embed.mychannels.video/production/193993',
  65         'only_matching': True,
  66     }, {
  67         'url': 'https://mychannels.video/embed/193993',
  68         'only_matching': True,
  69     }, {
  70         'url': 'https://embed.mychannels.video/embed/193993',
  71         'only_matching': True,
  72     }]
  73
  74     @staticmethod
  75     def _extract_urls(webpage):
  76         entries = []
  77         for element in re.findall(r'(<div[^>]+data-mychannels-type="video"[^>]*>)', webpage):
  78             mychannels_id = extract_attributes(element).get('data-mychannels-id')
  79             if mychannels_id:
  80                 entries.append('https://mychannels.video/embed/' + mychannels_id)
  81         return entries
  82
  83     def _real_extract(self, url):
  84         production_id = self._match_id(url)
  85         production = self._download_json(
  86             'https://embed.mychannels.video/sdk/production/' + production_id,
  87             production_id, query={'options': 'UUUU_default'})['productions'][0]
  88         title = production['title']
  89
  90         formats = []
  91         for source in (production.get('sources') or []):
  92             src = source.get('src')
  93             if not src:
  94                 continue
  95             ext = mimetype2ext(source.get('type'))
  96             if ext == 'm3u8':
  97                 formats.extend(self._extract_m3u8_formats(
  98                     src, production_id, 'mp4', 'm3u8_native',
  99                     m3u8_id='hls', fatal=False))
 100             else:
 101                 formats.append({
 102                     'ext': ext,
 103                     'url': src,
 104                 })
 105         self._sort_formats(formats)
 106
 107         return {
 108             'id': production_id,
 109             'title': title,
 110             'formats': formats,
 111             'thumbnail': production.get('posterUrl'),
 112             'timestamp': parse_iso8601(production.get('publicationDate'), ' '),
 113             'duration': int_or_none(production.get('duration')) or None,
 114         }