From cfd7f2a6365e4d4ed9036b7fd873747be5e91d44 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 27 May 2018 18:24:37 +0700 Subject: [PATCH] [apa] Add extractor (closes #15041, closes #15672) --- youtube_dl/extractor/apa.py | 94 ++++++++++++++++++++++++++++++ youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/generic.py | 23 ++++++++ 3 files changed, 118 insertions(+) create mode 100644 youtube_dl/extractor/apa.py diff --git a/youtube_dl/extractor/apa.py b/youtube_dl/extractor/apa.py new file mode 100644 index 000000000..a30a935aa --- /dev/null +++ b/youtube_dl/extractor/apa.py @@ -0,0 +1,94 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + determine_ext, + js_to_json, +) + + +class APAIE(InfoExtractor): + _VALID_URL = r'https?://[^/]+\.apa\.at/embed/(?P[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})' + _TESTS = [{ + 'url': 'http://uvp.apa.at/embed/293f6d17-692a-44e3-9fd5-7b178f3a1029', + 'md5': '2b12292faeb0a7d930c778c7a5b4759b', + 'info_dict': { + 'id': 'jjv85FdZ', + 'ext': 'mp4', + 'title': '"Blau ist mysteriƶs": Die Blue Man Group im Interview', + 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 254, + 'timestamp': 1519211149, + 'upload_date': '20180221', + }, + }, { + 'url': 'https://uvp-apapublisher.sf.apa.at/embed/2f94e9e6-d945-4db2-9548-f9a41ebf7b78', + 'only_matching': True, + }, { + 'url': 'http://uvp-rma.sf.apa.at/embed/70404cca-2f47-4855-bbb8-20b1fae58f76', + 'only_matching': True, + }, { + 'url': 'http://uvp-kleinezeitung.sf.apa.at/embed/f1c44979-dba2-4ebf-b021-e4cf2cac3c81', + 'only_matching': True, + }] + + @staticmethod + def _extract_urls(webpage): + return [ + mobj.group('url') + for mobj in re.finditer( + r']+\bsrc=(["\'])(?P(?:https?:)?//[^/]+\.apa\.at/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}.*?)\1', + webpage)] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + jwplatform_id = self._search_regex( + r'media[iI]d\s*:\s*["\'](?P[a-zA-Z0-9]{8})', webpage, + 'jwplatform id', default=None) + + if jwplatform_id: + return self.url_result( + 'jwplatform:' + jwplatform_id, ie='JWPlatform', + video_id=video_id) + + sources = self._parse_json( + self._search_regex( + r'sources\s*=\s*(\[.+?\])\s*;', webpage, 'sources'), + video_id, transform_source=js_to_json) + + formats = [] + for source in sources: + if not isinstance(source, dict): + continue + source_url = source.get('file') + if not source_url or not isinstance(source_url, compat_str): + continue + ext = determine_ext(source_url) + if ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + source_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + else: + formats.append({ + 'url': source_url, + }) + self._sort_formats(formats) + + thumbnail = self._search_regex( + r'image\s*:\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, + 'thumbnail', fatal=False, group='url') + + return { + 'id': video_id, + 'title': video_id, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 2f485012f..5f829c72c 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -44,6 +44,7 @@ from .anysex import AnySexIE from .aol import AolIE from .allocine import AllocineIE from .aliexpress import AliExpressLiveIE +from .apa import APAIE from .aparat import AparatIE from .appleconnect import AppleConnectIE from .appletrailers import ( diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 0292e0458..dad951b75 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -110,6 +110,7 @@ from .xfileshare import XFileShareIE from .cloudflarestream import CloudflareStreamIE from .peertube import PeerTubeIE from .indavideo import IndavideoEmbedIE +from .apa import APAIE class GenericIE(InfoExtractor): @@ -2041,6 +2042,23 @@ class GenericIE(InfoExtractor): 'skip_download': True, }, }, + { + # APA embed via JWPlatform embed + 'url': 'http://www.vol.at/blue-man-group/5593454', + 'info_dict': { + 'id': 'jjv85FdZ', + 'ext': 'mp4', + 'title': '"Blau ist mysteriƶs": Die Blue Man Group im Interview', + 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 254, + 'timestamp': 1519211149, + 'upload_date': '20180221', + }, + 'params': { + 'skip_download': True, + }, + }, { 'url': 'http://share-videos.se/auto/video/83645793?uid=13', 'md5': 'b68d276de422ab07ee1d49388103f457', @@ -3068,6 +3086,11 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key()) + apa_urls = APAIE._extract_urls(webpage) + if apa_urls: + return self.playlist_from_matches( + apa_urls, video_id, video_title, ie=APAIE.ie_key()) + sharevideos_urls = [mobj.group('url') for mobj in re.finditer( r']+?\bsrc\s*=\s*(["\'])(?P(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1', webpage)]