Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/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 _real_initialize(self):
  26         self._login()
  27
  28     def _login(self):
  29         username, password = self._get_login_info()
  30         if username is None:
  31             return
  32
  33         # Sets some cookies
  34         _, urlh = self._download_webpage_handle(
  35             self._LOGIN_URL, None, 'Downloading login popup')
  36
  37         def is_logged(url_handle):
  38             return self._LOGIN_URL not in url_handle.geturl()
  39
  40         # Already logged in
  41         if is_logged(urlh):
  42             return
  43
  44         login_form = {
  45             'signin[email]': username,
  46             'signin[password]': password,
  47             'signin[remember]': 'on',
  48         }
  49
  50         response, urlh = self._download_webpage_handle(
  51             self._LOGIN_URL, None, 'Logging in',
  52             data=urlencode_postdata(login_form))
  53
  54         # Logged in successfully
  55         if is_logged(urlh):
  56             return
  57
  58         errors = self._html_search_regex(
  59             r'(?s)<ul[^>]+class=["\']error_list[^>]+>(.+?)</ul>', response,
  60             'errors', default=None)
  61         if errors:
  62             raise ExtractorError('Unable to login: %s' % errors, expected=True)
  63         raise ExtractorError('Unable to log in')
  64
  65
  66 class LecturioIE(LecturioBaseIE):
  67     _VALID_URL = r'''(?x)
  68                     https://
  69                         (?:
  70                             app\.lecturio\.com/([^/]+/(?P<nt>[^/?#&]+)\.lecture|(?:\#/)?lecture/c/\d+/(?P<id>\d+))|
  71                             (?:www\.)?lecturio\.de/[^/]+/(?P<nt_de>[^/?#&]+)\.vortrag
  72                         )
  73                     '''
  74     _TESTS = [{
  75         'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos',
  76         'md5': '9a42cf1d8282a6311bf7211bbde26fde',
  77         'info_dict': {
  78             'id': '39634',
  79             'ext': 'mp4',
  80             'title': 'Important Concepts and Terms — Introduction to Microbiology',
  81         },
  82         'skip': 'Requires lecturio account credentials',
  83     }, {
  84         'url': 'https://www.lecturio.de/jura/oeffentliches-recht-staatsexamen.vortrag',
  85         'only_matching': True,
  86     }, {
  87         'url': 'https://app.lecturio.com/#/lecture/c/6434/39634',
  88         'only_matching': True,
  89     }]
  90
  91     _CC_LANGS = {
  92         'Arabic': 'ar',
  93         'Bulgarian': 'bg',
  94         'German': 'de',
  95         'English': 'en',
  96         'Spanish': 'es',
  97         'Persian': 'fa',
  98         'French': 'fr',
  99         'Japanese': 'ja',
 100         'Polish': 'pl',
 101         'Pashto': 'ps',
 102         'Russian': 'ru',
 103     }
 104
 105     def _real_extract(self, url):
 106         mobj = re.match(self._VALID_URL, url)
 107         nt = mobj.group('nt') or mobj.group('nt_de')
 108         lecture_id = mobj.group('id')
 109         display_id = nt or lecture_id
 110         api_path = 'lectures/' + lecture_id if lecture_id else 'lecture/' + nt + '.json'
 111         video = self._download_json(
 112             self._API_BASE_URL + api_path, display_id)
 113         title = video['title'].strip()
 114         if not lecture_id:
 115             pid = video.get('productId') or video.get('uid')
 116             if pid:
 117                 spid = pid.split('_')
 118                 if spid and len(spid) == 2:
 119                     lecture_id = spid[1]
 120
 121         formats = []
 122         for format_ in video['content']['media']:
 123             if not isinstance(format_, dict):
 124                 continue
 125             file_ = format_.get('file')
 126             if not file_:
 127                 continue
 128             ext = determine_ext(file_)
 129             if ext == 'smil':
 130                 # smil contains only broken RTMP formats anyway
 131                 continue
 132             file_url = url_or_none(file_)
 133             if not file_url:
 134                 continue
 135             label = str_or_none(format_.get('label'))
 136             filesize = int_or_none(format_.get('fileSize'))
 137             f = {
 138                 'url': file_url,
 139                 'format_id': label,
 140                 'filesize': float_or_none(filesize, invscale=1000)
 141             }
 142             if label:
 143                 mobj = re.match(r'(\d+)p\s*\(([^)]+)\)', label)
 144                 if mobj:
 145                     f.update({
 146                         'format_id': mobj.group(2),
 147                         'height': int(mobj.group(1)),
 148                     })
 149             formats.append(f)
 150         self._sort_formats(formats)
 151
 152         subtitles = {}
 153         automatic_captions = {}
 154         captions = video.get('captions') or []
 155         for cc in captions:
 156             cc_url = cc.get('url')
 157             if not cc_url:
 158                 continue
 159             cc_label = cc.get('translatedCode')
 160             lang = cc.get('languageCode') or self._search_regex(
 161                 r'/([a-z]{2})_', cc_url, 'lang',
 162                 default=cc_label.split()[0] if cc_label else 'en')
 163             original_lang = self._search_regex(
 164                 r'/[a-z]{2}_([a-z]{2})_', cc_url, 'original lang',
 165                 default=None)
 166             sub_dict = (automatic_captions
 167                         if 'auto-translated' in cc_label or original_lang
 168                         else subtitles)
 169             sub_dict.setdefault(self._CC_LANGS.get(lang, lang), []).append({
 170                 'url': cc_url,
 171             })
 172
 173         return {
 174             'id': lecture_id or nt,
 175             'title': title,
 176             'formats': formats,
 177             'subtitles': subtitles,
 178             'automatic_captions': automatic_captions,
 179         }
 180
 181
 182 class LecturioCourseIE(LecturioBaseIE):
 183     _VALID_URL = r'https://app\.lecturio\.com/(?:[^/]+/(?P<nt>[^/?#&]+)\.course|(?:#/)?course/c/(?P<id>\d+))'
 184     _TESTS = [{
 185         'url': 'https://app.lecturio.com/medical-courses/microbiology-introduction.course#/',
 186         'info_dict': {
 187             'id': 'microbiology-introduction',
 188             'title': 'Microbiology: Introduction',
 189             'description': 'md5:13da8500c25880c6016ae1e6d78c386a',
 190         },
 191         'playlist_count': 45,
 192         'skip': 'Requires lecturio account credentials',
 193     }, {
 194         'url': 'https://app.lecturio.com/#/course/c/6434',
 195         'only_matching': True,
 196     }]
 197
 198     def _real_extract(self, url):
 199         nt, course_id = re.match(self._VALID_URL, url).groups()
 200         display_id = nt or course_id
 201         api_path = 'courses/' + course_id if course_id else 'course/content/' + nt + '.json'
 202         course = self._download_json(
 203             self._API_BASE_URL + api_path, display_id)
 204         entries = []
 205         for lecture in course.get('lectures', []):
 206             lecture_id = str_or_none(lecture.get('id'))
 207             lecture_url = lecture.get('url')
 208             if lecture_url:
 209                 lecture_url = urljoin(url, lecture_url)
 210             else:
 211                 lecture_url = 'https://app.lecturio.com/#/lecture/c/%s/%s' % (course_id, lecture_id)
 212             entries.append(self.url_result(
 213                 lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
 214         return self.playlist_result(
 215             entries, display_id, course.get('title'),
 216             clean_html(course.get('description')))
 217
 218
 219 class LecturioDeCourseIE(LecturioBaseIE):
 220     _VALID_URL = r'https://(?:www\.)?lecturio\.de/[^/]+/(?P<id>[^/?#&]+)\.kurs'
 221     _TEST = {
 222         'url': 'https://www.lecturio.de/jura/grundrechte.kurs',
 223         'only_matching': True,
 224     }
 225
 226     def _real_extract(self, url):
 227         display_id = self._match_id(url)
 228
 229         webpage = self._download_webpage(url, display_id)
 230
 231         entries = []
 232         for mobj in re.finditer(
 233                 r'(?s)<td[^>]+\bdata-lecture-id=["\'](?P<id>\d+).+?\bhref=(["\'])(?P<url>(?:(?!\2).)+\.vortrag)\b[^>]+>',
 234                 webpage):
 235             lecture_url = urljoin(url, mobj.group('url'))
 236             lecture_id = mobj.group('id')
 237             entries.append(self.url_result(
 238                 lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
 239
 240         title = self._search_regex(
 241             r'<h1[^>]*>([^<]+)', webpage, 'title', default=None)
 242
 243         return self.playlist_result(entries, display_id, title)