Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/yesjapan.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     HEADRequest,
   7     get_element_by_attribute,
   8     parse_iso8601,
   9 )
  10
  11
  12 class YesJapanIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?yesjapan\.com/video/(?P<slug>[A-Za-z0-9\-]*)_(?P<id>[A-Za-z0-9]+)\.html'
  14     _TEST = {
  15         'url': 'http://www.yesjapan.com/video/japanese-in-5-20-wa-and-ga-particle-usages_726497834.html',
  16         'md5': 'f0be416314e5be21a12b499b330c21cf',
  17         'info_dict': {
  18             'id': '726497834',
  19             'title': 'Japanese in 5! #20 - WA And GA Particle Usages',
  20             'description': 'This should clear up some issues most students of Japanese encounter with WA and GA....',
  21             'ext': 'mp4',
  22             'timestamp': 1416391590,
  23             'upload_date': '20141119',
  24             'thumbnail': r're:^https?://.*\.jpg$',
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30
  31         webpage = self._download_webpage(url, video_id)
  32         title = self._og_search_title(webpage)
  33         video_url = self._og_search_video_url(webpage)
  34         description = self._og_search_description(webpage)
  35         thumbnail = self._og_search_thumbnail(webpage)
  36
  37         timestamp = None
  38         submit_info = get_element_by_attribute('class', 'pm-submit-data', webpage)
  39         if submit_info:
  40             timestamp = parse_iso8601(self._search_regex(
  41                 r'datetime="([^"]+)"', submit_info, 'upload date', fatal=False, default=None))
  42
  43         # attempt to resolve the final URL in order to get a proper extension
  44         redirect_req = HEADRequest(video_url)
  45         req = self._request_webpage(
  46             redirect_req, video_id, note='Resolving final URL', errnote='Could not resolve final URL', fatal=False)
  47         if req:
  48             video_url = req.geturl()
  49
  50         formats = [{
  51             'format_id': 'sd',
  52             'url': video_url,
  53         }]
  54
  55         return {
  56             'id': video_id,
  57             'title': title,
  58             'formats': formats,
  59             'description': description,
  60             'timestamp': timestamp,
  61             'thumbnail': thumbnail,
  62         }