_ Git - youtube-dl/blob - youtube_dl/extractor/lrt.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     parse_duration,
   7     remove_end,
   8 )
   9
  10
  11 class LRTIE(InfoExtractor):
  12     IE_NAME = 'lrt.lt'
  13     _VALID_URL = r'https?://(?:www\.)?lrt\.lt/mediateka/irasas/(?P<id>[0-9]+)'
  14     _TEST = {
  15         'url': 'http://www.lrt.lt/mediateka/irasas/54391/',
  16         'info_dict': {
  17             'id': '54391',
  18             'ext': 'mp4',
  19             'title': 'Septynios Kauno dienos',
  20             'description': 'md5:24d84534c7dc76581e59f5689462411a',
  21             'duration': 1783,
  22         },
  23         'params': {
  24             'skip_download': True,  # m3u8 download
  25         },
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30         webpage = self._download_webpage(url, video_id)
  31
  32         title = remove_end(self._og_search_title(webpage), ' - LRT')
  33         m3u8_url = self._search_regex(
  34             r'file\s*:\s*(["\'])(?P<url>.+?)\1\s*\+\s*location\.hash\.substring\(1\)',
  35             webpage, 'm3u8 url', group='url')
  36         formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
  37
  38         thumbnail = self._og_search_thumbnail(webpage)
  39         description = self._og_search_description(webpage)
  40         duration = parse_duration(self._search_regex(
  41             r'var\s+record_len\s*=\s*(["\'])(?P<duration>[0-9]+:[0-9]+:[0-9]+)\1',
  42             webpage, 'duration', default=None, group='duration'))
  43
  44         return {
  45             'id': video_id,
  46             'title': title,
  47             'formats': formats,
  48             'thumbnail': thumbnail,
  49             'description': description,
  50             'duration': duration,
  51         }