Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/lecture2go.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     determine_ext,
   9     parse_duration,
  10     int_or_none,
  11 )
  12
  13
  14 class Lecture2GoIE(InfoExtractor):
  15     _VALID_URL = r'https?://lecture2go\.uni-hamburg\.de/veranstaltungen/-/v/(?P<id>\d+)'
  16     _TEST = {
  17         'url': 'https://lecture2go.uni-hamburg.de/veranstaltungen/-/v/17473',
  18         'md5': 'ac02b570883020d208d405d5a3fd2f7f',
  19         'info_dict': {
  20             'id': '17473',
  21             'ext': 'flv',
  22             'title': '2 - Endliche Automaten und reguläre Sprachen',
  23             'creator': 'Frank Heitmann',
  24             'duration': 5220,
  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 = self._html_search_regex(r'<em[^>]+class="title">(.+)</em>', webpage, 'title')
  33
  34         formats = []
  35         for url in set(re.findall(r'"src","([^"]+)"', webpage)):
  36             ext = determine_ext(url)
  37             if ext == 'f4m':
  38                 formats.extend(self._extract_f4m_formats(url, video_id))
  39             elif ext == 'm3u8':
  40                 formats.extend(self._extract_m3u8_formats(url, video_id))
  41             else:
  42                 formats.append({
  43                     'url': url,
  44                 })
  45
  46         self._sort_formats(formats)
  47
  48         creator = self._html_search_regex(
  49             r'<div[^>]+id="description">([^<]+)</div>', webpage, 'creator', fatal=False)
  50         duration = parse_duration(self._html_search_regex(
  51             r'Duration:\s*</em>\s*<em[^>]*>([^<]+)</em>', webpage, 'duration', fatal=False))
  52         view_count = int_or_none(self._html_search_regex(
  53             r'Views:\s*</em>\s*<em[^>]+>(\d+)</em>', webpage, 'view count', fatal=False))
  54
  55         return {
  56             'id': video_id,
  57             'title': title,
  58             'formats': formats,
  59             'creator': creator,
  60             'duration': duration,
  61             'view_count': view_count,
  62         }