yt_dlp/extractor/teamtreehouse.py

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