Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/frontendmasters.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 (
   8     compat_str,
   9     compat_urlparse,
  10 )
  11 from ..utils import (
  12     ExtractorError,
  13     parse_duration,
  14     url_or_none,
  15     urlencode_postdata,
  16 )
  17
  18
  19 class FrontendMastersBaseIE(InfoExtractor):
  20     _API_BASE = 'https://api.frontendmasters.com/v1/kabuki'
  21     _LOGIN_URL = 'https://frontendmasters.com/login/'
  22
  23     _NETRC_MACHINE = 'frontendmasters'
  24
  25     _QUALITIES = {
  26         'low': {'width': 480, 'height': 360},
  27         'mid': {'width': 1280, 'height': 720},
  28         'high': {'width': 1920, 'height': 1080}
  29     }
  30
  31     def _real_initialize(self):
  32         self._login()
  33
  34     def _login(self):
  35         (username, password) = self._get_login_info()
  36         if username is None:
  37             return
  38
  39         login_page = self._download_webpage(
  40             self._LOGIN_URL, None, 'Downloading login page')
  41
  42         login_form = self._hidden_inputs(login_page)
  43
  44         login_form.update({
  45             'username': username,
  46             'password': password
  47         })
  48
  49         post_url = self._search_regex(
  50             r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
  51             'post_url', default=self._LOGIN_URL, group='url')
  52
  53         if not post_url.startswith('http'):
  54             post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
  55
  56         response = self._download_webpage(
  57             post_url, None, 'Logging in', data=urlencode_postdata(login_form),
  58             headers={'Content-Type': 'application/x-www-form-urlencoded'})
  59
  60         # Successful login
  61         if any(p in response for p in (
  62                 'wp-login.php?action=logout', '>Logout')):
  63             return
  64
  65         error = self._html_search_regex(
  66             r'class=(["\'])(?:(?!\1).)*\bMessageAlert\b(?:(?!\1).)*\1[^>]*>(?P<error>[^<]+)<',
  67             response, 'error message', default=None, group='error')
  68         if error:
  69             raise ExtractorError('Unable to login: %s' % error, expected=True)
  70         raise ExtractorError('Unable to log in')
  71
  72
  73 class FrontendMastersPageBaseIE(FrontendMastersBaseIE):
  74     def _download_course(self, course_name, url):
  75         return self._download_json(
  76             '%s/courses/%s' % (self._API_BASE, course_name), course_name,
  77             'Downloading course JSON', headers={'Referer': url})
  78
  79     @staticmethod
  80     def _extract_chapters(course):
  81         chapters = []
  82         lesson_elements = course.get('lessonElements')
  83         if isinstance(lesson_elements, list):
  84             chapters = [url_or_none(e) for e in lesson_elements if url_or_none(e)]
  85         return chapters
  86
  87     @staticmethod
  88     def _extract_lesson(chapters, lesson_id, lesson):
  89         title = lesson.get('title') or lesson_id
  90         display_id = lesson.get('slug')
  91         description = lesson.get('description')
  92         thumbnail = lesson.get('thumbnail')
  93
  94         chapter_number = None
  95         index = lesson.get('index')
  96         element_index = lesson.get('elementIndex')
  97         if (isinstance(index, int) and isinstance(element_index, int)
  98                 and index < element_index):
  99             chapter_number = element_index - index
 100         chapter = (chapters[chapter_number - 1]
 101                    if chapter_number - 1 < len(chapters) else None)
 102
 103         duration = None
 104         timestamp = lesson.get('timestamp')
 105         if isinstance(timestamp, compat_str):
 106             mobj = re.search(
 107                 r'(?P<start>\d{1,2}:\d{1,2}:\d{1,2})\s*-(?P<end>\s*\d{1,2}:\d{1,2}:\d{1,2})',
 108                 timestamp)
 109             if mobj:
 110                 duration = parse_duration(mobj.group('end')) - parse_duration(
 111                     mobj.group('start'))
 112
 113         return {
 114             '_type': 'url_transparent',
 115             'url': 'frontendmasters:%s' % lesson_id,
 116             'ie_key': FrontendMastersIE.ie_key(),
 117             'id': lesson_id,
 118             'display_id': display_id,
 119             'title': title,
 120             'description': description,
 121             'thumbnail': thumbnail,
 122             'duration': duration,
 123             'chapter': chapter,
 124             'chapter_number': chapter_number,
 125         }
 126
 127
 128 class FrontendMastersIE(FrontendMastersBaseIE):
 129     _VALID_URL = r'(?:frontendmasters:|https?://api\.frontendmasters\.com/v\d+/kabuki/video/)(?P<id>[^/]+)'
 130     _TESTS = [{
 131         'url': 'https://api.frontendmasters.com/v1/kabuki/video/a2qogef6ba',
 132         'md5': '7f161159710d6b7016a4f4af6fcb05e2',
 133         'info_dict': {
 134             'id': 'a2qogef6ba',
 135             'ext': 'mp4',
 136             'title': 'a2qogef6ba',
 137         },
 138         'skip': 'Requires FrontendMasters account credentials',
 139     }, {
 140         'url': 'frontendmasters:a2qogef6ba',
 141         'only_matching': True,
 142     }]
 143
 144     def _real_extract(self, url):
 145         lesson_id = self._match_id(url)
 146
 147         source_url = '%s/video/%s/source' % (self._API_BASE, lesson_id)
 148
 149         formats = []
 150         for ext in ('webm', 'mp4'):
 151             for quality in ('low', 'mid', 'high'):
 152                 resolution = self._QUALITIES[quality].copy()
 153                 format_id = '%s-%s' % (ext, quality)
 154                 format_url = self._download_json(
 155                     source_url, lesson_id,
 156                     'Downloading %s source JSON' % format_id, query={
 157                         'f': ext,
 158                         'r': resolution['height'],
 159                     }, headers={
 160                         'Referer': url,
 161                     }, fatal=False)['url']
 162
 163                 if not format_url:
 164                     continue
 165
 166                 f = resolution.copy()
 167                 f.update({
 168                     'url': format_url,
 169                     'ext': ext,
 170                     'format_id': format_id,
 171                 })
 172                 formats.append(f)
 173         self._sort_formats(formats)
 174
 175         subtitles = {
 176             'en': [{
 177                 'url': '%s/transcripts/%s.vtt' % (self._API_BASE, lesson_id),
 178             }]
 179         }
 180
 181         return {
 182             'id': lesson_id,
 183             'title': lesson_id,
 184             'formats': formats,
 185             'subtitles': subtitles
 186         }
 187
 188
 189 class FrontendMastersLessonIE(FrontendMastersPageBaseIE):
 190     _VALID_URL = r'https?://(?:www\.)?frontendmasters\.com/courses/(?P<course_name>[^/]+)/(?P<lesson_name>[^/]+)'
 191     _TEST = {
 192         'url': 'https://frontendmasters.com/courses/web-development/tools',
 193         'info_dict': {
 194             'id': 'a2qogef6ba',
 195             'display_id': 'tools',
 196             'ext': 'mp4',
 197             'title': 'Tools',
 198             'description': 'md5:82c1ea6472e88ed5acd1829fe992e4f7',
 199             'thumbnail': r're:^https?://.*\.jpg$',
 200             'chapter': 'Introduction',
 201             'chapter_number': 1,
 202         },
 203         'params': {
 204             'skip_download': True,
 205         },
 206         'skip': 'Requires FrontendMasters account credentials',
 207     }
 208
 209     def _real_extract(self, url):
 210         mobj = re.match(self._VALID_URL, url)
 211         course_name, lesson_name = mobj.group('course_name', 'lesson_name')
 212
 213         course = self._download_course(course_name, url)
 214
 215         lesson_id, lesson = next(
 216             (video_id, data)
 217             for video_id, data in course['lessonData'].items()
 218             if data.get('slug') == lesson_name)
 219
 220         chapters = self._extract_chapters(course)
 221         return self._extract_lesson(chapters, lesson_id, lesson)
 222
 223
 224 class FrontendMastersCourseIE(FrontendMastersPageBaseIE):
 225     _VALID_URL = r'https?://(?:www\.)?frontendmasters\.com/courses/(?P<id>[^/]+)'
 226     _TEST = {
 227         'url': 'https://frontendmasters.com/courses/web-development/',
 228         'info_dict': {
 229             'id': 'web-development',
 230             'title': 'Introduction to Web Development',
 231             'description': 'md5:9317e6e842098bf725d62360e52d49a6',
 232         },
 233         'playlist_count': 81,
 234         'skip': 'Requires FrontendMasters account credentials',
 235     }
 236
 237     @classmethod
 238     def suitable(cls, url):
 239         return False if FrontendMastersLessonIE.suitable(url) else super(
 240             FrontendMastersBaseIE, cls).suitable(url)
 241
 242     def _real_extract(self, url):
 243         course_name = self._match_id(url)
 244
 245         course = self._download_course(course_name, url)
 246
 247         chapters = self._extract_chapters(course)
 248
 249         lessons = sorted(
 250             course['lessonData'].values(), key=lambda data: data['index'])
 251
 252         entries = []
 253         for lesson in lessons:
 254             lesson_name = lesson.get('slug')
 255             if not lesson_name:
 256                 continue
 257             lesson_id = lesson.get('hash') or lesson.get('statsId')
 258             entries.append(self._extract_lesson(chapters, lesson_id, lesson))
 259
 260         title = course.get('title')
 261         description = course.get('description')
 262
 263         return self.playlist_result(entries, course_name, title, description)