From 7453999580f2809153a84420d3ca72b24186c02b Mon Sep 17 00:00:00 2001 From: =?utf8?q?Sergey=20M=E2=80=A4?= Date: Sat, 1 Apr 2017 00:25:27 +0700 Subject: [PATCH] [packtpub] Add extractor (closes #12610) --- youtube_dl/extractor/extractors.py | 4 + youtube_dl/extractor/packtpub.py | 138 +++++++++++++++++++++++++++++ 2 files changed, 142 insertions(+) create mode 100644 youtube_dl/extractor/packtpub.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 43933ad5b..6ad7444fe 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -729,6 +729,10 @@ from .orf import ( ORFFM4IE, ORFIPTVIE, ) +from .packtpub import ( + PacktPubIE, + PacktPubCourseIE, +) from .pandatv import PandaTVIE from .pandoratv import PandoraTVIE from .parliamentliveuk import ParliamentLiveUKIE diff --git a/youtube_dl/extractor/packtpub.py b/youtube_dl/extractor/packtpub.py new file mode 100644 index 000000000..881f3bcc7 --- /dev/null +++ b/youtube_dl/extractor/packtpub.py @@ -0,0 +1,138 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + clean_html, + ExtractorError, + remove_end, + strip_or_none, + unified_timestamp, + urljoin, +) + + +class PacktPubBaseIE(InfoExtractor): + _PACKT_BASE = 'https://www.packtpub.com' + _MAPT_REST = '%s/mapt-rest' % _PACKT_BASE + + +class PacktPubIE(PacktPubBaseIE): + _VALID_URL = r'https?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P\d+)/(?P\d+)/(?P\d+)' + + _TEST = { + 'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215/20528/20530/Project+Intro', + 'md5': '1e74bd6cfd45d7d07666f4684ef58f70', + 'info_dict': { + 'id': '20530', + 'ext': 'mp4', + 'title': 'Project Intro', + 'thumbnail': r're:(?i)^https?://.*\.jpg', + 'timestamp': 1490918400, + 'upload_date': '20170331', + }, + } + + 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') + + 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')['data'] + + content = video.get('content') + if not content: + raise ExtractorError('This video is locked', expected=True) + + video_url = content['file'] + + 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')) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + } + + +class PacktPubCourseIE(PacktPubBaseIE): + _VALID_URL = r'(?Phttps?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P\d+))' + _TEST = { + 'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215', + 'info_dict': { + 'id': '9781787122215', + 'title': 'Learn Nodejs by building 12 projects [Video]', + }, + 'playlist_count': 90, + } + + @classmethod + def suitable(cls, url): + return False if PacktPubIE.suitable(url) else super( + PacktPubCourseIE, cls).suitable(url) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + url, course_id = mobj.group('url', 'id') + + course = self._download_json( + '%s/products/%s/metadata' % (self._MAPT_REST, course_id), + course_id)['data'] + + 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): + continue + chapter_info = { + 'chapter': chapter.get('title'), + 'chapter_number': chapter_num, + 'chapter_id': chapter.get('id'), + } + for section in children: + if section.get('type') != 'section': + continue + section_url = section.get('seoUrl') + if not isinstance(section_url, compat_str): + continue + entry = { + '_type': 'url_transparent', + 'url': urljoin(url + '/', section_url), + 'title': strip_or_none(section.get('title')), + 'description': clean_html(section.get('summary')), + 'ie_key': PacktPubIE.ie_key(), + } + entry.update(chapter_info) + entries.append(entry) + + return self.playlist_result(entries, course_id, course.get('title')) -- 2.22.2