From 69fcdb845b9744125161f514cb4166becbae2959 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 8 Jul 2018 00:48:23 +0700 Subject: [PATCH] [frontendmasters] Fix issues and improve extraction (closes #3661, closes #16328) --- youtube_dl/extractor/extractors.py | 7 +- youtube_dl/extractor/frontendmaster.py | 271 ------------------------ youtube_dl/extractor/frontendmasters.py | 262 +++++++++++++++++++++++ 3 files changed, 266 insertions(+), 274 deletions(-) delete mode 100644 youtube_dl/extractor/frontendmaster.py create mode 100644 youtube_dl/extractor/frontendmasters.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 265b4aa9d..ed532d77f 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -390,9 +390,10 @@ from .francetv import ( from .freesound import FreesoundIE from .freespeech import FreespeechIE from .freshlive import FreshLiveIE -from .frontendmaster import ( - FrontEndMasterIE, - FrontEndMasterCourseIE +from .frontendmasters import ( + FrontendMastersIE, + FrontendMastersLessonIE, + FrontendMastersCourseIE ) from .funimation import FunimationIE from .funk import ( diff --git a/youtube_dl/extractor/frontendmaster.py b/youtube_dl/extractor/frontendmaster.py deleted file mode 100644 index 21e382da9..000000000 --- a/youtube_dl/extractor/frontendmaster.py +++ /dev/null @@ -1,271 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import collections -import re - -from .common import InfoExtractor -from ..compat import ( - compat_urlparse) -from ..utils import ( - ExtractorError, - urlencode_postdata, - qualities, unescapeHTML) - - -class FrontEndMasterBaseIE(InfoExtractor): - _API_BASE = 'https://api.frontendmasters.com/v1/kabuki/courses' - _VIDEO_BASE = 'http://www.frontendmasters.com/courses' - _CAPTIONS_BASE = 'https://api.frontendmasters.com/v1/kabuki/transcripts' - _COOKIES_BASE = 'https://api.frontendmasters.com' - _LOGIN_URL = 'https://frontendmasters.com/login/' - - _QUALITIES_PREFERENCE = ('low', 'medium', 'high') - _QUALITIES = { - 'low': {'width': 480, 'height': 360}, - 'medium': {'width': 1280, 'height': 720}, - 'high': {'width': 1920, 'height': 1080} - } - - AllowedQuality = collections.namedtuple('AllowedQuality', - ['ext', 'qualities']) - _ALLOWED_QUALITIES = [ - AllowedQuality('webm', ['low', 'medium', 'high']), - AllowedQuality('mp4', ['low', 'medium', 'high']) - ] - - def _real_initialize(self): - self._login() - - def _login(self): - (username, password) = self._get_login_info() - if username is None: - return - - login_page = self._download_webpage( - self._LOGIN_URL, None, 'Downloading login page') - - login_form = self._hidden_inputs(login_page) - - login_form.update({ - 'username': username, - 'password': password - }) - - post_url = self._search_regex( - r']+action=(["\'])(?P.+?)\1', login_page, - 'post_url', default=self._LOGIN_URL, group='url') - - if not post_url.startswith('http'): - post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url) - - response = self._download_webpage( - post_url, None, 'Logging in', - data=urlencode_postdata(login_form), - headers={'Content-Type': 'application/x-www-form-urlencoded'} - ) - - error = self._search_regex( - r']+class=["\']Message MessageAlert["\'][^>]*>' - r'([^<]+)' - r'', - response, 'error message', default=None) - - if error: - raise ExtractorError('Unable to login: %s' % unescapeHTML(error), - expected=True) - - def _download_course(self, course_id, url): - response = self._download_json( - '%s/%s' % (self._API_BASE, course_id), course_id, - 'Downloading course JSON', - headers={ - 'Content-Type': 'application/json;charset=utf-8', - 'Referer': url, - }) - return response - - @staticmethod - def _pair_section_video_element(lesson_elements): - sections = {} - current_section = None - current_section_number = 0 - for elem in lesson_elements: - if not isinstance(elem, int): - elem_name = elem - if not isinstance(elem_name, str): - # convert unicode to str - elem_name = elem.encode('utf-8') - (current_section, current_section_number) = \ - (elem_name, current_section_number + 1) - else: - if current_section: - sections[elem] = (current_section, current_section_number) - - return sections - - -class FrontEndMasterIE(FrontEndMasterBaseIE): - IE_NAME = 'frontend-masters' - _VALID_URL = r'https?://(?:www\.)?frontendmasters\.com/courses/' \ - r'(?P[a-z\-]+)/' \ - r'(?P[a-z\-]+)' - - _NETRC_MACHINE = 'frontendmasters' - - _TEST = { - 'url': 'https://frontendmasters.com/courses/web-development/tools', - 'md5': '7f161159710d6b7016a4f4af6fcb05e2', - 'info_dict': { - 'id': 'tools', - 'title': 'Tools', - 'display_id': 'tools', - 'description': 'md5:82c1ea6472e88ed5acd1829fe992e4f7', - 'ext': 'mp4' - }, - 'skip': 'Requires FrontendMasters account credentials', - } - - def _get_subtitles(self, video_hash, video_id): - captions = self._download_webpage( - '%s/%s.vtt' % (self._CAPTIONS_BASE, video_hash), video_id, - fatal=False) - if captions: - return { - 'en': [{ - 'ext': 'vtt', - 'data': captions - }] - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - course_id = mobj.group('courseid') - - course_json_content = self._download_course(course_id=course_id, - url=url) - - # Necessary to get mandatory informations like title and video_url - lesson_index = course_json_content.get('lessonSlugs').index(video_id) - lesson_hash = course_json_content.get('lessonHashes')[lesson_index] - lesson_data = course_json_content.get('lessonData')[lesson_hash] - # This is necessary to get the link for the video - lesson_source_base = lesson_data['sourceBase'] - - lesson_title = lesson_data['title'] - - # Some optional fields - lesson_description = lesson_data.get('description') - lesson_index = lesson_data.get('index') - lesson_slug = lesson_data.get('slug') - lesson_thumbnail_url = lesson_data.get('thumbnail') - lesson_section_elements = course_json_content.get('lessonElements') - - try: - course_sections_pairing = self._pair_section_video_element( - lesson_section_elements) - - lesson_section = \ - course_sections_pairing.get(lesson_index)[0] - - lesson_section_number = \ - course_sections_pairing.get(lesson_index)[1] - except Exception: - lesson_section = None - lesson_section_number = None - - video_request_url = '%s/source' - video_request_headers = { - 'origin': 'https://frontendmasters.com', - 'referer': lesson_source_base, - } - - quality_key = qualities(self._QUALITIES_PREFERENCE) - - formats = [] - for ext, qualities_ in self._ALLOWED_QUALITIES: - for quality in qualities_: - f = self._QUALITIES[quality].copy() - video_request_params = { - 'r': f['height'], - 'f': ext - } - video_response = self._download_json( - video_request_url % lesson_source_base, video_id, - query=video_request_params, headers=video_request_headers) - - video_url = video_response.get('url') - clip_f = f.copy() - clip_f.update({ - 'url': video_url, - 'ext': ext, - 'format_id': '%s-%s' % (ext, quality), - 'quality': quality_key(quality), - 'height': f['height'] - }) - formats.append(clip_f) - - self._sort_formats(formats) - - subtitles = self.extract_subtitles(lesson_hash, video_id) - - return { - 'id': video_id, - 'display_id': lesson_slug, - 'title': lesson_title, - 'description': lesson_description, - 'chapter': lesson_section, - 'chapter_number': lesson_section_number, - 'thumbnail': lesson_thumbnail_url, - 'formats': formats, - 'subtitles': subtitles - } - - -class FrontEndMasterCourseIE(FrontEndMasterBaseIE): - IE_NAME = 'frontend-masters:course' - _VALID_URL = r'https?://(?:www\.)?frontendmasters\.com/courses/(?P[a-z\-]+)/?$' - - _NETRC_MACHINE = 'frontendmasters' - - _TEST = { - 'url': 'https://frontendmasters.com/courses/javascript-basics/', - 'info_dict': { - 'id': 'javascript-basics', - 'title': 'Introduction to JavaScript Programming', - 'description': 'md5:269412fbb76d86954761599ad8e4cbc9' - }, - 'playlist_count': 19, - 'skip': 'Requires FrontendMasters account credentials' - } - - @classmethod - def suitable(cls, url): - return False if FrontEndMasterIE.suitable(url) else super(FrontEndMasterBaseIE, cls).suitable(url) - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - course_id = mobj.group('courseid') - course_json_content = self._download_course(course_id=course_id, - url=url) - - title = course_json_content.get('title') - description = course_json_content.get('description') - course_display_id = course_json_content.get('slug') - - videos_data = course_json_content.get('lessonData').values() - videos_data = sorted(videos_data, key=lambda video: video.get('index')) - - entries = [] - for video in videos_data: - video_slug = video.get('slug') - clip_url = '%s/%s/%s' % ( - self._VIDEO_BASE, course_display_id, video_slug) - entries.append({ - '_type': 'url_transparent', - 'url': clip_url, - 'ie_key': FrontEndMasterIE.ie_key() - }) - - return self.playlist_result(entries, course_id, title, description) diff --git a/youtube_dl/extractor/frontendmasters.py b/youtube_dl/extractor/frontendmasters.py new file mode 100644 index 000000000..770db46d0 --- /dev/null +++ b/youtube_dl/extractor/frontendmasters.py @@ -0,0 +1,262 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import ( + compat_str, + compat_urlparse, +) +from ..utils import ( + ExtractorError, + parse_duration, + urlencode_postdata, +) + + +class FrontendMastersBaseIE(InfoExtractor): + _API_BASE = 'https://api.frontendmasters.com/v1/kabuki' + _LOGIN_URL = 'https://frontendmasters.com/login/' + + _NETRC_MACHINE = 'frontendmasters' + + _QUALITIES = { + 'low': {'width': 480, 'height': 360}, + 'mid': {'width': 1280, 'height': 720}, + 'high': {'width': 1920, 'height': 1080} + } + + def _real_initialize(self): + self._login() + + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + + login_page = self._download_webpage( + self._LOGIN_URL, None, 'Downloading login page') + + login_form = self._hidden_inputs(login_page) + + login_form.update({ + 'username': username, + 'password': password + }) + + post_url = self._search_regex( + r']+action=(["\'])(?P.+?)\1', login_page, + 'post_url', default=self._LOGIN_URL, group='url') + + if not post_url.startswith('http'): + post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url) + + response = self._download_webpage( + post_url, None, 'Logging in', data=urlencode_postdata(login_form), + headers={'Content-Type': 'application/x-www-form-urlencoded'}) + + # Successful login + if any(p in response for p in ( + 'wp-login.php?action=logout', '>Logout')): + return + + error = self._html_search_regex( + r'class=(["\'])(?:(?!\1).)*\bMessageAlert\b(?:(?!\1).)*\1[^>]*>(?P[^<]+)<', + response, 'error message', default=None, group='error') + if error: + raise ExtractorError('Unable to login: %s' % error, expected=True) + raise ExtractorError('Unable to log in') + + +class FrontendMastersPageBaseIE(FrontendMastersBaseIE): + def _download_course(self, course_name, url): + return self._download_json( + '%s/courses/%s' % (self._API_BASE, course_name), course_name, + 'Downloading course JSON', headers={'Referer': url}) + + @staticmethod + def _extract_chapters(course): + chapters = [] + lesson_elements = course.get('lessonElements') + if isinstance(lesson_elements, list): + chapters = [e for e in lesson_elements if isinstance(e, compat_str)] + return chapters + + @staticmethod + def _extract_lesson(chapters, lesson_id, lesson): + title = lesson.get('title') or lesson_id + display_id = lesson.get('slug') + description = lesson.get('description') + thumbnail = lesson.get('thumbnail') + + chapter_number = None + index = lesson.get('index') + element_index = lesson.get('elementIndex') + if (isinstance(index, int) and isinstance(element_index, int) and + index < element_index): + chapter_number = element_index - index + chapter = (chapters[chapter_number - 1] + if chapter_number - 1 < len(chapters) else None) + + duration = None + timestamp = lesson.get('timestamp') + if isinstance(timestamp, compat_str): + mobj = re.search( + r'(?P\d{1,2}:\d{1,2}:\d{1,2})\s*-(?P\s*\d{1,2}:\d{1,2}:\d{1,2})', + timestamp) + if mobj: + duration = parse_duration(mobj.group('end')) - parse_duration( + mobj.group('start')) + + return { + '_type': 'url_transparent', + 'url': 'frontendmasters:%s' % lesson_id, + 'ie_key': FrontendMastersIE.ie_key(), + 'id': lesson_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'chapter': chapter, + 'chapter_number': chapter_number, + } + + +class FrontendMastersIE(FrontendMastersBaseIE): + _VALID_URL = r'(?:frontendmasters:|https?://api\.frontendmasters\.com/v\d+/kabuki/video/)(?P[^/]+)' + _TESTS = [{ + 'url': 'https://api.frontendmasters.com/v1/kabuki/video/a2qogef6ba', + 'md5': '7f161159710d6b7016a4f4af6fcb05e2', + 'info_dict': { + 'id': 'a2qogef6ba', + 'ext': 'mp4', + 'title': 'a2qogef6ba', + }, + 'skip': 'Requires FrontendMasters account credentials', + }, { + 'url': 'frontendmasters:a2qogef6ba', + 'only_matching': True, + }] + + def _real_extract(self, url): + lesson_id = self._match_id(url) + + source_url = '%s/video/%s/source' % (self._API_BASE, lesson_id) + + formats = [] + for ext in ('webm', 'mp4'): + for quality in ('low', 'mid', 'high'): + resolution = self._QUALITIES[quality].copy() + format_id = '%s-%s' % (ext, quality) + format_url = self._download_json( + source_url, lesson_id, + 'Downloading %s source JSON' % format_id, query={ + 'f': ext, + 'r': resolution['height'], + }, headers={ + 'Referer': url, + }, fatal=False)['url'] + + if not format_url: + continue + + f = resolution.copy() + f.update({ + 'url': format_url, + 'ext': ext, + 'format_id': format_id, + }) + formats.append(f) + self._sort_formats(formats) + + subtitles = { + 'en': [{ + 'url': '%s/transcripts/%s.vtt' % (self._API_BASE, lesson_id), + }] + } + + return { + 'id': lesson_id, + 'title': lesson_id, + 'formats': formats, + 'subtitles': subtitles + } + + +class FrontendMastersLessonIE(FrontendMastersPageBaseIE): + _VALID_URL = r'https?://(?:www\.)?frontendmasters\.com/courses/(?P[^/]+)/(?P[^/]+)' + _TEST = { + 'url': 'https://frontendmasters.com/courses/web-development/tools', + 'info_dict': { + 'id': 'a2qogef6ba', + 'display_id': 'tools', + 'ext': 'mp4', + 'title': 'Tools', + 'description': 'md5:82c1ea6472e88ed5acd1829fe992e4f7', + 'thumbnail': r're:^https?://.*\.jpg$', + 'chapter': 'Introduction', + 'chapter_number': 1, + }, + 'params': { + 'skip_download': True, + }, + 'skip': 'Requires FrontendMasters account credentials', + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + course_name, lesson_name = mobj.group('course_name', 'lesson_name') + + course = self._download_course(course_name, url) + + lesson_id, lesson = next( + (video_id, data) + for video_id, data in course['lessonData'].items() + if data.get('slug') == lesson_name) + + chapters = self._extract_chapters(course) + return self._extract_lesson(chapters, lesson_id, lesson) + + +class FrontendMastersCourseIE(FrontendMastersPageBaseIE): + _VALID_URL = r'https?://(?:www\.)?frontendmasters\.com/courses/(?P[^/]+)' + _TEST = { + 'url': 'https://frontendmasters.com/courses/web-development/', + 'info_dict': { + 'id': 'web-development', + 'title': 'Introduction to Web Development', + 'description': 'md5:9317e6e842098bf725d62360e52d49a6', + }, + 'playlist_count': 81, + 'skip': 'Requires FrontendMasters account credentials', + } + + @classmethod + def suitable(cls, url): + return False if FrontendMastersLessonIE.suitable(url) else super( + FrontendMastersBaseIE, cls).suitable(url) + + def _real_extract(self, url): + course_name = self._match_id(url) + + course = self._download_course(course_name, url) + + chapters = self._extract_chapters(course) + + lessons = sorted( + course['lessonData'].values(), key=lambda data: data['index']) + + entries = [] + for lesson in lessons: + lesson_name = lesson.get('slug') + if not lesson_name: + continue + lesson_id = lesson.get('hash') or lesson.get('statsId') + entries.append(self._extract_lesson(chapters, lesson_id, lesson)) + + title = course.get('title') + description = course.get('description') + + return self.playlist_result(entries, course_name, title, description)