Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/teamtreehouse.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     clean_html,
   9     determine_ext,
  10     ExtractorError,
  11     float_or_none,
  12     get_element_by_class,
  13     get_element_by_id,
  14     parse_duration,
  15     remove_end,
  16     urlencode_postdata,
  17     urljoin,
  18 )
  19
  20
  21 class TeamTreeHouseIE(InfoExtractor):
  22     _VALID_URL = r'https?://(?:www\.)?teamtreehouse\.com/library/(?P<id>[^/]+)'
  23     _TESTS = [{
  24         # Course
  25         'url': 'https://teamtreehouse.com/library/introduction-to-user-authentication-in-php',
  26         'info_dict': {
  27             'id': 'introduction-to-user-authentication-in-php',
  28             'title': 'Introduction to User Authentication in PHP',
  29             'description': 'md5:405d7b4287a159b27ddf30ca72b5b053',
  30         },
  31         'playlist_mincount': 24,
  32     }, {
  33         # WorkShop
  34         'url': 'https://teamtreehouse.com/library/deploying-a-react-app',
  35         'info_dict': {
  36             'id': 'deploying-a-react-app',
  37             'title': 'Deploying a React App',
  38             'description': 'md5:10a82e3ddff18c14ac13581c9b8e5921',
  39         },
  40         'playlist_mincount': 4,
  41     }, {
  42         # Video
  43         'url': 'https://teamtreehouse.com/library/application-overview-2',
  44         'info_dict': {
  45             'id': 'application-overview-2',
  46             'ext': 'mp4',
  47             'title': 'Application Overview',
  48             'description': 'md5:4b0a234385c27140a4378de5f1e15127',
  49         },
  50         'expected_warnings': ['This is just a preview'],
  51     }]
  52     _NETRC_MACHINE = 'teamtreehouse'
  53
  54     def _real_initialize(self):
  55         email, password = self._get_login_info()
  56         if email is None:
  57             return
  58
  59         signin_page = self._download_webpage(
  60             'https://teamtreehouse.com/signin',
  61             None, 'Downloading signin page')
  62         data = self._form_hidden_inputs('new_user_session', signin_page)
  63         data.update({
  64             'user_session[email]': email,
  65             'user_session[password]': password,
  66         })
  67         error_message = get_element_by_class('error-message', self._download_webpage(
  68             'https://teamtreehouse.com/person_session',
  69             None, 'Logging in', data=urlencode_postdata(data)))
  70         if error_message:
  71             raise ExtractorError(clean_html(error_message), expected=True)
  72
  73     def _real_extract(self, url):
  74         display_id = self._match_id(url)
  75         webpage = self._download_webpage(url, display_id)
  76         title = self._html_search_meta(['og:title', 'twitter:title'], webpage)
  77         description = self._html_search_meta(
  78             ['description', 'og:description', 'twitter:description'], webpage)
  79         entries = self._parse_html5_media_entries(url, webpage, display_id)
  80         if entries:
  81             info = entries[0]
  82
  83             for subtitles in info.get('subtitles', {}).values():
  84                 for subtitle in subtitles:
  85                     subtitle['ext'] = determine_ext(subtitle['url'], 'srt')
  86
  87             is_preview = 'data-preview="true"' in webpage
  88             if is_preview:
  89                 self.report_warning(
  90                     'This is just a preview. You need to be signed in with a Basic account to download the entire video.', display_id)
  91                 duration = 30
  92             else:
  93                 duration = float_or_none(self._search_regex(
  94                     r'data-duration="(\d+)"', webpage, 'duration'), 1000)
  95                 if not duration:
  96                     duration = parse_duration(get_element_by_id(
  97                         'video-duration', webpage))
  98
  99             info.update({
 100                 'id': display_id,
 101                 'title': title,
 102                 'description': description,
 103                 'duration': duration,
 104             })
 105             return info
 106         else:
 107             def extract_urls(html, extract_info=None):
 108                 for path in re.findall(r'<a[^>]+href="([^"]+)"', html):
 109                     page_url = urljoin(url, path)
 110                     entry = {
 111                         '_type': 'url_transparent',
 112                         'id': self._match_id(page_url),
 113                         'url': page_url,
 114                         'id_key': self.ie_key(),
 115                     }
 116                     if extract_info:
 117                         entry.update(extract_info)
 118                     entries.append(entry)
 119
 120             workshop_videos = self._search_regex(
 121                 r'(?s)<ul[^>]+id="workshop-videos"[^>]*>(.+?)</ul>',
 122                 webpage, 'workshop videos', default=None)
 123             if workshop_videos:
 124                 extract_urls(workshop_videos)
 125             else:
 126                 stages_path = self._search_regex(
 127                     r'(?s)<div[^>]+id="syllabus-stages"[^>]+data-url="([^"]+)"',
 128                     webpage, 'stages path')
 129                 if stages_path:
 130                     stages_page = self._download_webpage(
 131                         urljoin(url, stages_path), display_id, 'Downloading stages page')
 132                     for chapter_number, (chapter, steps_list) in enumerate(re.findall(r'(?s)<h2[^>]*>\s*(.+?)\s*</h2>.+?<ul[^>]*>(.+?)</ul>', stages_page), 1):
 133                         extract_urls(steps_list, {
 134                             'chapter': chapter,
 135                             'chapter_number': chapter_number,
 136                         })
 137                     title = remove_end(title, ' Course')
 138
 139             return self.playlist_result(
 140                 entries, display_id, title, description)