_ Git - youtube-dl/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 ..compat import compat_str
   8 from ..utils import (
   9     determine_ext,
  10     extract_attributes,
  11     ExtractorError,
  12     float_or_none,
  13     int_or_none,
  14     str_or_none,
  15     url_or_none,
  16     urlencode_postdata,
  17     urljoin,
  18 )
  19
  20
  21 class LecturioBaseIE(InfoExtractor):
  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 compat_str(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'https://app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.lecture'
  68     _TEST = {
  69         'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos',
  70         'md5': 'f576a797a5b7a5e4e4bbdfc25a6a6870',
  71         'info_dict': {
  72             'id': '39634',
  73             'ext': 'mp4',
  74             'title': 'Important Concepts and Terms – Introduction to Microbiology',
  75         },
  76         'skip': 'Requires lecturio account credentials',
  77     }
  78
  79     _CC_LANGS = {
  80         'German': 'de',
  81         'English': 'en',
  82         'Spanish': 'es',
  83         'French': 'fr',
  84         'Polish': 'pl',
  85         'Russian': 'ru',
  86     }
  87
  88     def _real_extract(self, url):
  89         display_id = self._match_id(url)
  90
  91         webpage = self._download_webpage(
  92             'https://app.lecturio.com/en/lecture/%s/player.html' % display_id,
  93             display_id)
  94
  95         lecture_id = self._search_regex(
  96             r'lecture_id\s*=\s*(?:L_)?(\d+)', webpage, 'lecture id')
  97
  98         api_url = self._search_regex(
  99             r'lectureDataLink\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
 100             'api url', group='url')
 101
 102         video = self._download_json(api_url, display_id)
 103
 104         title = video['title'].strip()
 105
 106         formats = []
 107         for format_ in video['content']['media']:
 108             if not isinstance(format_, dict):
 109                 continue
 110             file_ = format_.get('file')
 111             if not file_:
 112                 continue
 113             ext = determine_ext(file_)
 114             if ext == 'smil':
 115                 # smil contains only broken RTMP formats anyway
 116                 continue
 117             file_url = url_or_none(file_)
 118             if not file_url:
 119                 continue
 120             label = str_or_none(format_.get('label'))
 121             filesize = int_or_none(format_.get('fileSize'))
 122             formats.append({
 123                 'url': file_url,
 124                 'format_id': label,
 125                 'filesize': float_or_none(filesize, invscale=1000)
 126             })
 127         self._sort_formats(formats)
 128
 129         subtitles = {}
 130         automatic_captions = {}
 131         cc = self._parse_json(
 132             self._search_regex(
 133                 r'subtitleUrls\s*:\s*({.+?})\s*,', webpage, 'subtitles',
 134                 default='{}'), display_id, fatal=False)
 135         for cc_label, cc_url in cc.items():
 136             cc_url = url_or_none(cc_url)
 137             if not cc_url:
 138                 continue
 139             sub_dict = automatic_captions if 'auto-translated' in cc_label else subtitles
 140             lang = self._search_regex(
 141                 r'/([a-z]{2})_', cc_url, 'lang', default=cc_label.split()[0])
 142             sub_dict.setdefault(self._CC_LANGS.get(lang, lang), []).append({
 143                 'url': cc_url,
 144             })
 145
 146         return {
 147             'id': lecture_id,
 148             'title': title,
 149             'formats': formats,
 150             'subtitles': subtitles,
 151             'automatic_captions': automatic_captions,
 152         }
 153
 154
 155 class LecturioCourseIE(LecturioBaseIE):
 156     _VALID_URL = r'https://app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.course'
 157     _TEST = {
 158         'url': 'https://app.lecturio.com/medical-courses/microbiology-introduction.course#/',
 159         'info_dict': {
 160             'id': 'microbiology-introduction',
 161             'title': 'Microbiology: Introduction',
 162         },
 163         'playlist_count': 45,
 164         'skip': 'Requires lecturio account credentials',
 165     }
 166
 167     def _real_extract(self, url):
 168         display_id = self._match_id(url)
 169
 170         webpage = self._download_webpage(url, display_id)
 171
 172         entries = []
 173         for mobj in re.finditer(
 174                 r'(?s)<[^>]+\bdata-url=(["\'])(?:(?!\1).)+\.lecture\b[^>]+>',
 175                 webpage):
 176             params = extract_attributes(mobj.group(0))
 177             lecture_url = urljoin(url, params.get('data-url'))
 178             lecture_id = params.get('data-id')
 179             entries.append(self.url_result(
 180                 lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
 181
 182         title = self._search_regex(
 183             r'<span[^>]+class=["\']content-title[^>]+>([^<]+)', webpage,
 184             'title', default=None)
 185
 186         return self.playlist_result(entries, display_id, title)