X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9d6a3ba754469c85b7f0f88714203f99ac69087a..04c6e7e9539d48169931f1911a39ed223d44cf2b:/youtube_dl/extractor/packtpub.py?ds=sidebyside diff --git a/youtube_dl/extractor/packtpub.py b/youtube_dl/extractor/packtpub.py index 56a2a10..11ad3b3 100644 --- a/youtube_dl/extractor/packtpub.py +++ b/youtube_dl/extractor/packtpub.py @@ -5,28 +5,29 @@ import re from .common import InfoExtractor from ..compat import ( - compat_str, + # compat_str, compat_HTTPError, ) from ..utils import ( clean_html, ExtractorError, - remove_end, + # remove_end, + str_or_none, strip_or_none, unified_timestamp, - urljoin, + # urljoin, ) class PacktPubBaseIE(InfoExtractor): - _PACKT_BASE = 'https://www.packtpub.com' - _MAPT_REST = '%s/mapt-rest' % _PACKT_BASE + # _PACKT_BASE = 'https://www.packtpub.com' + _STATIC_PRODUCTS_BASE = 'https://static.packt-cdn.com/products/' class PacktPubIE(PacktPubBaseIE): - _VALID_URL = r'https?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P\d+)/(?P\d+)/(?P\d+)' + _VALID_URL = r'https?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P\d+)/(?P[^/]+)/(?P[^/]+)(?:/(?P[^/?&#]+))?' - _TEST = { + _TESTS = [{ 'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215/20528/20530/Project+Intro', 'md5': '1e74bd6cfd45d7d07666f4684ef58f70', 'info_dict': { @@ -37,7 +38,13 @@ class PacktPubIE(PacktPubBaseIE): 'timestamp': 1490918400, 'upload_date': '20170331', }, - } + }, { + 'url': 'https://subscription.packtpub.com/video/web_development/9781787122215/20528/20530/project-intro', + 'only_matching': True, + }, { + 'url': 'https://subscription.packtpub.com/video/programming/9781838988906/p1/video1_1/business-card-project', + 'only_matching': True, + }] _NETRC_MACHINE = 'packtpub' _TOKEN = None @@ -47,9 +54,9 @@ class PacktPubIE(PacktPubBaseIE): return try: self._TOKEN = self._download_json( - self._MAPT_REST + '/users/tokens', None, + 'https://services.packtpub.com/auth-v1/users/tokens', None, 'Downloading Authorization Token', data=json.dumps({ - 'email': username, + 'username': username, 'password': password, }).encode())['data']['access'] except ExtractorError as e: @@ -58,67 +65,57 @@ class PacktPubIE(PacktPubBaseIE): raise ExtractorError(message, expected=True) raise - def _handle_error(self, response): - if response.get('status') != 'success': - raise ExtractorError( - '% said: %s' % (self.IE_NAME, response['message']), - expected=True) - - def _download_json(self, *args, **kwargs): - response = super(PacktPubIE, self)._download_json(*args, **kwargs) - self._handle_error(response) - return response - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - course_id, chapter_id, video_id = mobj.group( - 'course_id', 'chapter_id', 'id') + course_id, chapter_id, video_id, display_id = re.match(self._VALID_URL, url).groups() headers = {} if self._TOKEN: headers['Authorization'] = 'Bearer ' + self._TOKEN - video = self._download_json( - '%s/users/me/products/%s/chapters/%s/sections/%s' - % (self._MAPT_REST, course_id, chapter_id, video_id), video_id, - 'Downloading JSON video', headers=headers)['data'] - - content = video.get('content') - if not content: - self.raise_login_required('This video is locked') - - video_url = content['file'] + try: + video_url = self._download_json( + 'https://services.packtpub.com/products-v1/products/%s/%s/%s' % (course_id, chapter_id, video_id), video_id, + 'Downloading JSON video', headers=headers)['data'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: + self.raise_login_required('This video is locked') + raise - metadata = self._download_json( - '%s/products/%s/chapters/%s/sections/%s/metadata' - % (self._MAPT_REST, course_id, chapter_id, video_id), - video_id)['data'] + # TODO: find a better way to avoid duplicating course requests + # metadata = self._download_json( + # '%s/products/%s/chapters/%s/sections/%s/metadata' + # % (self._MAPT_REST, course_id, chapter_id, video_id), + # video_id)['data'] - title = metadata['pageTitle'] - course_title = metadata.get('title') - if course_title: - title = remove_end(title, ' - %s' % course_title) - timestamp = unified_timestamp(metadata.get('publicationDate')) - thumbnail = urljoin(self._PACKT_BASE, metadata.get('filepath')) + # title = metadata['pageTitle'] + # course_title = metadata.get('title') + # if course_title: + # title = remove_end(title, ' - %s' % course_title) + # timestamp = unified_timestamp(metadata.get('publicationDate')) + # thumbnail = urljoin(self._PACKT_BASE, metadata.get('filepath')) return { 'id': video_id, 'url': video_url, - 'title': title, - 'thumbnail': thumbnail, - 'timestamp': timestamp, + 'title': display_id or video_id, # title, + # 'thumbnail': thumbnail, + # 'timestamp': timestamp, } class PacktPubCourseIE(PacktPubBaseIE): - _VALID_URL = r'(?Phttps?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P\d+))' - _TEST = { + _VALID_URL = r'(?Phttps?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P\d+))' + _TESTS = [{ 'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215', 'info_dict': { 'id': '9781787122215', 'title': 'Learn Nodejs by building 12 projects [Video]', + 'description': 'md5:489da8d953f416e51927b60a1c7db0aa', }, 'playlist_count': 90, - } + }, { + 'url': 'https://subscription.packtpub.com/video/web_development/9781787122215', + 'only_matching': True, + }] @classmethod def suitable(cls, url): @@ -130,35 +127,38 @@ class PacktPubCourseIE(PacktPubBaseIE): url, course_id = mobj.group('url', 'id') course = self._download_json( - '%s/products/%s/metadata' % (self._MAPT_REST, course_id), - course_id)['data'] + self._STATIC_PRODUCTS_BASE + '%s/toc' % course_id, course_id) + metadata = self._download_json( + self._STATIC_PRODUCTS_BASE + '%s/summary' % course_id, + course_id, fatal=False) or {} entries = [] - for chapter_num, chapter in enumerate(course['tableOfContents'], 1): - if chapter.get('type') != 'chapter': - continue - children = chapter.get('children') - if not isinstance(children, list): + for chapter_num, chapter in enumerate(course['chapters'], 1): + chapter_id = str_or_none(chapter.get('id')) + sections = chapter.get('sections') + if not chapter_id or not isinstance(sections, list): continue chapter_info = { 'chapter': chapter.get('title'), 'chapter_number': chapter_num, - 'chapter_id': chapter.get('id'), + 'chapter_id': chapter_id, } - for section in children: - if section.get('type') != 'section': - continue - section_url = section.get('seoUrl') - if not isinstance(section_url, compat_str): + for section in sections: + section_id = str_or_none(section.get('id')) + if not section_id or section.get('contentType') != 'video': continue entry = { '_type': 'url_transparent', - 'url': urljoin(url + '/', section_url), + 'url': '/'.join([url, chapter_id, section_id]), 'title': strip_or_none(section.get('title')), 'description': clean_html(section.get('summary')), + 'thumbnail': metadata.get('coverImage'), + 'timestamp': unified_timestamp(metadata.get('publicationDate')), 'ie_key': PacktPubIE.ie_key(), } entry.update(chapter_info) entries.append(entry) - return self.playlist_result(entries, course_id, course.get('title')) + return self.playlist_result( + entries, course_id, metadata.get('title'), + clean_html(metadata.get('about')))