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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class EggheadCourseIE(InfoExtractor):
  10     IE_DESC = 'egghead.io course'
  11     IE_NAME = 'egghead:course'
  12     _VALID_URL = r'https://egghead\.io/courses/(?P<id>[a-zA-Z_0-9-]+)'
  13     _TEST = {
  14         'url': 'https://egghead.io/courses/professor-frisby-introduces-composable-functional-javascript',
  15         'playlist_count': 29,
  16         'info_dict': {
  17             'id': 'professor-frisby-introduces-composable-functional-javascript',
  18             'title': 'Professor Frisby Introduces Composable Functional JavaScript',
  19             'description': 're:(?s)^This course teaches the ubiquitous.*You\'ll start composing functionality before you know it.$',
  20         },
  21     }
  22
  23     def _real_extract(self, url):
  24         playlist_id = self._match_id(url)
  25         webpage = self._download_webpage(url, playlist_id)
  26
  27         title = self._html_search_regex(r'<h1 class="title">([^<]+)</h1>', webpage, 'title')
  28         ul = self._search_regex(r'(?s)<ul class="series-lessons-list">(.*?)</ul>', webpage, 'session list')
  29
  30         found = re.findall(r'(?s)<a class="[^"]*"\s*href="([^"]+)">\s*<li class="item', ul)
  31         entries = [self.url_result(m) for m in found]
  32
  33         return {
  34             '_type': 'playlist',
  35             'id': playlist_id,
  36             'title': title,
  37             'description': self._og_search_description(webpage),
  38             'entries': entries,
  39         }