youtube_dl/extractor/upskill.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from .wistia import WistiaIE
   7 from ..compat import compat_str
   8 from ..utils import (
   9     clean_html,
  10     ExtractorError,
  11     get_element_by_class,
  12     urlencode_postdata,
  13     urljoin,
  14 )
  15
  16
  17 class UpskillBaseIE(InfoExtractor):
  18     _LOGIN_URL = 'http://upskillcourses.com/sign_in'
  19     _NETRC_MACHINE = 'upskill'
  20
  21     def _real_initialize(self):
  22         self._login()
  23
  24     def _login(self):
  25         username, password = self._get_login_info()
  26         if username is None:
  27             return
  28
  29         login_page, urlh = self._download_webpage_handle(
  30             self._LOGIN_URL, None, 'Downloading login page')
  31
  32         login_url = compat_str(urlh.geturl())
  33
  34         login_form = self._hidden_inputs(login_page)
  35
  36         login_form.update({
  37             'user[email]': username,
  38             'user[password]': password,
  39         })
  40
  41         post_url = self._search_regex(
  42             r'<form[^>]+action=(["\'])(?P<url>(?:(?!\1).)+)\1', login_page,
  43             'post url', default=login_url, group='url')
  44
  45         if not post_url.startswith('http'):
  46             post_url = urljoin(login_url, post_url)
  47
  48         response = self._download_webpage(
  49             post_url, None, 'Logging in',
  50             data=urlencode_postdata(login_form),
  51             headers={
  52                 'Content-Type': 'application/x-www-form-urlencoded',
  53                 'Referer': login_url,
  54             })
  55
  56         # Successful login
  57         if any(re.search(p, response) for p in (
  58                 r'class=["\']user-signout',
  59                 r'<a[^>]+\bhref=["\']/sign_out',
  60                 r'>\s*Log out\s*<')):
  61             return
  62
  63         message = get_element_by_class('alert', response)
  64         if message is not None:
  65             raise ExtractorError(
  66                 'Unable to login: %s' % clean_html(message), expected=True)
  67
  68         raise ExtractorError('Unable to log in')
  69
  70
  71 class UpskillIE(UpskillBaseIE):
  72     _VALID_URL = r'https?://(?:www\.)?upskillcourses\.com/courses/[^/]+/lectures/(?P<id>\d+)'
  73
  74     _TESTS = [{
  75         'url': 'http://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100',
  76         'info_dict': {
  77             'id': 'uzw6zw58or',
  78             'ext': 'mp4',
  79             'title': 'Welcome to the Course!',
  80             'description': 'md5:8d66c13403783370af62ca97a7357bdd',
  81             'duration': 138.763,
  82             'timestamp': 1479846621,
  83             'upload_date': '20161122',
  84         },
  85         'params': {
  86             'skip_download': True,
  87         },
  88     }, {
  89         'url': 'http://upskillcourses.com/courses/119763/lectures/1747100',
  90         'only_matching': True,
  91     }]
  92
  93     def _real_extract(self, url):
  94         video_id = self._match_id(url)
  95
  96         webpage = self._download_webpage(url, video_id)
  97
  98         wistia_url = WistiaIE._extract_url(webpage)
  99         if not wistia_url:
 100             if any(re.search(p, webpage) for p in (
 101                     r'class=["\']lecture-contents-locked',
 102                     r'>\s*Lecture contents locked',
 103                     r'id=["\']lecture-locked')):
 104                 self.raise_login_required('Lecture contents locked')
 105
 106         title = self._og_search_title(webpage, default=None)
 107
 108         return {
 109             '_type': 'url_transparent',
 110             'url': wistia_url,
 111             'ie_key': WistiaIE.ie_key(),
 112             'title': title,
 113         }
 114
 115
 116 class UpskillCourseIE(UpskillBaseIE):
 117     _VALID_URL = r'https?://(?:www\.)?upskillcourses\.com/courses/(?:enrolled/)?(?P<id>[^/?#&]+)'
 118     _TESTS = [{
 119         'url': 'http://upskillcourses.com/courses/essential-web-developer-course/',
 120         'info_dict': {
 121             'id': '119763',
 122             'title': 'The Essential Web Developer Course (Free)',
 123         },
 124         'playlist_count': 192,
 125     }, {
 126         'url': 'http://upskillcourses.com/courses/119763/',
 127         'only_matching': True,
 128     }, {
 129         'url': 'http://upskillcourses.com/courses/enrolled/119763',
 130         'only_matching': True,
 131     }]
 132
 133     @classmethod
 134     def suitable(cls, url):
 135         return False if UpskillIE.suitable(url) else super(
 136             UpskillCourseIE, cls).suitable(url)
 137
 138     def _real_extract(self, url):
 139         course_id = self._match_id(url)
 140
 141         webpage = self._download_webpage(url, course_id)
 142
 143         course_id = self._search_regex(
 144             r'data-course-id=["\'](\d+)', webpage, 'course id',
 145             default=course_id)
 146
 147         entries = []
 148
 149         for mobj in re.finditer(
 150                 r'(?s)(?P<li><li[^>]+class=(["\'])(?:(?!\2).)*?section-item[^>]+>.+?</li>)',
 151                 webpage):
 152             li = mobj.group('li')
 153             if 'fa-youtube-play' not in li:
 154                 continue
 155             lecture_url = self._search_regex(
 156                 r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1', li,
 157                 'lecture url', default=None, group='url')
 158             if not lecture_url:
 159                 continue
 160             lecture_id = self._search_regex(
 161                 r'/lectures/(\d+)', lecture_url, 'lecture id', default=None)
 162             title = self._html_search_regex(
 163                 r'<span[^>]+class=["\']lecture-name[^>]+>([^<]+)', li,
 164                 'title', default=None)
 165             entries.append(
 166                 self.url_result(
 167                     urljoin('http://upskillcourses.com/', lecture_url),
 168                     ie=UpskillIE.ie_key(), video_id=lecture_id,
 169                     video_title=clean_html(title)))
 170
 171         course_title = self._html_search_regex(
 172             (r'(?s)<img[^>]+class=["\']course-image[^>]+>\s*<h\d>(.+?)</h',
 173              r'(?s)<h\d[^>]+class=["\']course-title[^>]+>(.+?)</h'),
 174             webpage, 'course title', fatal=False)
 175
 176         return self.playlist_result(entries, course_id, course_title)