yt_dlp/extractor/airmozilla.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 )
   9
  10
  11 class AirMozillaIE(InfoExtractor):
  12     _VALID_URL = r'https?://air\.mozilla\.org/(?P<id>[0-9a-z-]+)/?'
  13     _TEST = {
  14         'url': 'https://air.mozilla.org/privacy-lab-a-meetup-for-privacy-minded-people-in-san-francisco/',
  15         'md5': '8d02f53ee39cf006009180e21df1f3ba',
  16         'info_dict': {
  17             'id': '6x4q2w',
  18             'ext': 'mp4',
  19             'title': 'Privacy Lab - a meetup for privacy minded people in San Francisco',
  20             'thumbnail': r're:https?://.*/poster\.jpg',
  21             'description': 'Brings together privacy professionals and others interested in privacy at for-profits, non-profits, and NGOs in an effort to contribute to the state of the ecosystem...',
  22             'timestamp': 1422487800,
  23             'upload_date': '20150128',
  24             'location': 'SFO Commons',
  25             'duration': 3780,
  26             'view_count': int,
  27             'categories': ['Main', 'Privacy'],
  28         }
  29     }
  30
  31     def _real_extract(self, url):
  32         display_id = self._match_id(url)
  33         webpage = self._download_webpage(url, display_id)
  34         video_id = self._html_search_regex(r'//vid\.ly/(.*?)/embed', webpage, 'id')
  35
  36         embed_script = self._download_webpage('https://vid.ly/{0}/embed'.format(video_id), video_id)
  37         jwconfig = self._parse_json(self._search_regex(
  38             r'initCallback\((.*)\);', embed_script, 'metadata'), video_id)['config']
  39
  40         info_dict = self._parse_jwplayer_data(jwconfig, video_id)
  41         view_count = int_or_none(self._html_search_regex(
  42             r'Views since archived: ([0-9]+)',
  43             webpage, 'view count', fatal=False))
  44         timestamp = parse_iso8601(self._html_search_regex(
  45             r'<time datetime="(.*?)"', webpage, 'timestamp', fatal=False))
  46         duration = parse_duration(self._search_regex(
  47             r'Duration:\s*(\d+\s*hours?\s*\d+\s*minutes?)',
  48             webpage, 'duration', fatal=False))
  49
  50         info_dict.update({
  51             'id': video_id,
  52             'title': self._og_search_title(webpage),
  53             'url': self._og_search_url(webpage),
  54             'display_id': display_id,
  55             'description': self._og_search_description(webpage),
  56             'timestamp': timestamp,
  57             'location': self._html_search_regex(r'Location: (.*)', webpage, 'location', default=None),
  58             'duration': duration,
  59             'view_count': view_count,
  60             'categories': re.findall(r'<a href=".*?" class="channel">(.*?)</a>', webpage),
  61         })
  62
  63         return info_dict