yt_dlp/extractor/lecturio.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     int_or_none,
  13     str_or_none,
  14     url_or_none,
  15     urlencode_postdata,
  16     urljoin,
  17 )
  18
  19
  20 class LecturioBaseIE(InfoExtractor):
  21     _API_BASE_URL = 'https://app.lecturio.com/api/en/latest/html5/'
  22     _LOGIN_URL = 'https://app.lecturio.com/en/login'
  23     _NETRC_MACHINE = 'lecturio'
  24
  25     def _perform_login(self, username, password):
  26         # Sets some cookies
  27         _, urlh = self._download_webpage_handle(
  28             self._LOGIN_URL, None, 'Downloading login popup')
  29
  30         def is_logged(url_handle):
  31             return self._LOGIN_URL not in url_handle.geturl()
  32
  33         # Already logged in
  34         if is_logged(urlh):
  35             return
  36
  37         login_form = {
  38             'signin[email]': username,
  39             'signin[password]': password,
  40             'signin[remember]': 'on',
  41         }
  42
  43         response, urlh = self._download_webpage_handle(
  44             self._LOGIN_URL, None, 'Logging in',
  45             data=urlencode_postdata(login_form))
  46
  47         # Logged in successfully
  48         if is_logged(urlh):
  49             return
  50
  51         errors = self._html_search_regex(
  52             r'(?s)<ul[^>]+class=["\']error_list[^>]+>(.+?)</ul>', response,
  53             'errors', default=None)
  54         if errors:
  55             raise ExtractorError('Unable to login: %s' % errors, expected=True)
  56         raise ExtractorError('Unable to log in')
  57
  58
  59 class LecturioIE(LecturioBaseIE):
  60     _VALID_URL = r'''(?x)
  61                     https://
  62                         (?:
  63                             app\.lecturio\.com/([^/]+/(?P<nt>[^/?#&]+)\.lecture|(?:\#/)?lecture/c/\d+/(?P<id>\d+))|
  64                             (?:www\.)?lecturio\.de/[^/]+/(?P<nt_de>[^/?#&]+)\.vortrag
  65                         )
  66                     '''
  67     _TESTS = [{
  68         'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos',
  69         'md5': '9a42cf1d8282a6311bf7211bbde26fde',
  70         'info_dict': {
  71             'id': '39634',
  72             'ext': 'mp4',
  73             'title': 'Important Concepts and Terms — Introduction to Microbiology',
  74         },
  75         'skip': 'Requires lecturio account credentials',
  76     }, {
  77         'url': 'https://www.lecturio.de/jura/oeffentliches-recht-staatsexamen.vortrag',
  78         'only_matching': True,
  79     }, {
  80         'url': 'https://app.lecturio.com/#/lecture/c/6434/39634',
  81         'only_matching': True,
  82     }]
  83
  84     _CC_LANGS = {
  85         'Arabic': 'ar',
  86         'Bulgarian': 'bg',
  87         'German': 'de',
  88         'English': 'en',
  89         'Spanish': 'es',
  90         'Persian': 'fa',
  91         'French': 'fr',
  92         'Japanese': 'ja',
  93         'Polish': 'pl',
  94         'Pashto': 'ps',
  95         'Russian': 'ru',
  96     }
  97
  98     def _real_extract(self, url):
  99         mobj = self._match_valid_url(url)
 100         nt = mobj.group('nt') or mobj.group('nt_de')
 101         lecture_id = mobj.group('id')
 102         display_id = nt or lecture_id
 103         api_path = 'lectures/' + lecture_id if lecture_id else 'lecture/' + nt + '.json'
 104         video = self._download_json(
 105             self._API_BASE_URL + api_path, display_id)
 106         title = video['title'].strip()
 107         if not lecture_id:
 108             pid = video.get('productId') or video.get('uid')
 109             if pid:
 110                 spid = pid.split('_')
 111                 if spid and len(spid) == 2:
 112                     lecture_id = spid[1]
 113
 114         formats = []
 115         for format_ in video['content']['media']:
 116             if not isinstance(format_, dict):
 117                 continue
 118             file_ = format_.get('file')
 119             if not file_:
 120                 continue
 121             ext = determine_ext(file_)
 122             if ext == 'smil':
 123                 # smil contains only broken RTMP formats anyway
 124                 continue
 125             file_url = url_or_none(file_)
 126             if not file_url:
 127                 continue
 128             label = str_or_none(format_.get('label'))
 129             filesize = int_or_none(format_.get('fileSize'))
 130             f = {
 131                 'url': file_url,
 132                 'format_id': label,
 133                 'filesize': float_or_none(filesize, invscale=1000)
 134             }
 135             if label:
 136                 mobj = re.match(r'(\d+)p\s*\(([^)]+)\)', label)
 137                 if mobj:
 138                     f.update({
 139                         'format_id': mobj.group(2),
 140                         'height': int(mobj.group(1)),
 141                     })
 142             formats.append(f)
 143         self._sort_formats(formats)
 144
 145         subtitles = {}
 146         automatic_captions = {}
 147         captions = video.get('captions') or []
 148         for cc in captions:
 149             cc_url = cc.get('url')
 150             if not cc_url:
 151                 continue
 152             cc_label = cc.get('translatedCode')
 153             lang = cc.get('languageCode') or self._search_regex(
 154                 r'/([a-z]{2})_', cc_url, 'lang',
 155                 default=cc_label.split()[0] if cc_label else 'en')
 156             original_lang = self._search_regex(
 157                 r'/[a-z]{2}_([a-z]{2})_', cc_url, 'original lang',
 158                 default=None)
 159             sub_dict = (automatic_captions
 160                         if 'auto-translated' in cc_label or original_lang
 161                         else subtitles)
 162             sub_dict.setdefault(self._CC_LANGS.get(lang, lang), []).append({
 163                 'url': cc_url,
 164             })
 165
 166         return {
 167             'id': lecture_id or nt,
 168             'title': title,
 169             'formats': formats,
 170             'subtitles': subtitles,
 171             'automatic_captions': automatic_captions,
 172         }
 173
 174
 175 class LecturioCourseIE(LecturioBaseIE):
 176     _VALID_URL = r'https://app\.lecturio\.com/(?:[^/]+/(?P<nt>[^/?#&]+)\.course|(?:#/)?course/c/(?P<id>\d+))'
 177     _TESTS = [{
 178         'url': 'https://app.lecturio.com/medical-courses/microbiology-introduction.course#/',
 179         'info_dict': {
 180             'id': 'microbiology-introduction',
 181             'title': 'Microbiology: Introduction',
 182             'description': 'md5:13da8500c25880c6016ae1e6d78c386a',
 183         },
 184         'playlist_count': 45,
 185         'skip': 'Requires lecturio account credentials',
 186     }, {
 187         'url': 'https://app.lecturio.com/#/course/c/6434',
 188         'only_matching': True,
 189     }]
 190
 191     def _real_extract(self, url):
 192         nt, course_id = self._match_valid_url(url).groups()
 193         display_id = nt or course_id
 194         api_path = 'courses/' + course_id if course_id else 'course/content/' + nt + '.json'
 195         course = self._download_json(
 196             self._API_BASE_URL + api_path, display_id)
 197         entries = []
 198         for lecture in course.get('lectures', []):
 199             lecture_id = str_or_none(lecture.get('id'))
 200             lecture_url = lecture.get('url')
 201             if lecture_url:
 202                 lecture_url = urljoin(url, lecture_url)
 203             else:
 204                 lecture_url = 'https://app.lecturio.com/#/lecture/c/%s/%s' % (course_id, lecture_id)
 205             entries.append(self.url_result(
 206                 lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
 207         return self.playlist_result(
 208             entries, display_id, course.get('title'),
 209             clean_html(course.get('description')))
 210
 211
 212 class LecturioDeCourseIE(LecturioBaseIE):
 213     _VALID_URL = r'https://(?:www\.)?lecturio\.de/[^/]+/(?P<id>[^/?#&]+)\.kurs'
 214     _TEST = {
 215         'url': 'https://www.lecturio.de/jura/grundrechte.kurs',
 216         'only_matching': True,
 217     }
 218
 219     def _real_extract(self, url):
 220         display_id = self._match_id(url)
 221
 222         webpage = self._download_webpage(url, display_id)
 223
 224         entries = []
 225         for mobj in re.finditer(
 226                 r'(?s)<td[^>]+\bdata-lecture-id=["\'](?P<id>\d+).+?\bhref=(["\'])(?P<url>(?:(?!\2).)+\.vortrag)\b[^>]+>',
 227                 webpage):
 228             lecture_url = urljoin(url, mobj.group('url'))
 229             lecture_id = mobj.group('id')
 230             entries.append(self.url_result(
 231                 lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
 232
 233         title = self._search_regex(
 234             r'<h1[^>]*>([^<]+)', webpage, 'title', default=None)
 235
 236         return self.playlist_result(entries, display_id, title)