yt_dlp/extractor/yesjapan.py

   1 from .common import InfoExtractor
   2 from ..networking import HEADRequest
   3 from ..utils import get_element_by_attribute, parse_iso8601
   4
   5
   6 class YesJapanIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?:www\.)?yesjapan\.com/video/(?P<slug>[A-Za-z0-9\-]*)_(?P<id>[A-Za-z0-9]+)\.html'
   8     _TEST = {
   9         'url': 'http://www.yesjapan.com/video/japanese-in-5-20-wa-and-ga-particle-usages_726497834.html',
  10         'md5': 'f0be416314e5be21a12b499b330c21cf',
  11         'info_dict': {
  12             'id': '726497834',
  13             'title': 'Japanese in 5! #20 - WA And GA Particle Usages',
  14             'description': 'This should clear up some issues most students of Japanese encounter with WA and GA....',
  15             'ext': 'mp4',
  16             'timestamp': 1416391590,
  17             'upload_date': '20141119',
  18             'thumbnail': r're:^https?://.*\.jpg$',
  19         }
  20     }
  21
  22     def _real_extract(self, url):
  23         video_id = self._match_id(url)
  24
  25         webpage = self._download_webpage(url, video_id)
  26         title = self._og_search_title(webpage)
  27         video_url = self._og_search_video_url(webpage)
  28         description = self._og_search_description(webpage)
  29         thumbnail = self._og_search_thumbnail(webpage)
  30
  31         timestamp = None
  32         submit_info = get_element_by_attribute('class', 'pm-submit-data', webpage)
  33         if submit_info:
  34             timestamp = parse_iso8601(self._search_regex(
  35                 r'datetime="([^"]+)"', submit_info, 'upload date', fatal=False, default=None))
  36
  37         # attempt to resolve the final URL in order to get a proper extension
  38         redirect_req = HEADRequest(video_url)
  39         req = self._request_webpage(
  40             redirect_req, video_id, note='Resolving final URL', errnote='Could not resolve final URL', fatal=False)
  41         if req:
  42             video_url = req.url
  43
  44         formats = [{
  45             'format_id': 'sd',
  46             'url': video_url,
  47         }]
  48
  49         return {
  50             'id': video_id,
  51             'title': title,
  52             'formats': formats,
  53             'description': description,
  54             'timestamp': timestamp,
  55             'thumbnail': thumbnail,
  56         }