diff options
author | Sergey M․ <dstftw@gmail.com> | 2018-05-26 01:25:40 +0700 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2018-05-26 01:25:40 +0700 |
commit | aee36ca832ec3a5696c40707098d97be0353e997 (patch) | |
tree | 79f67ef34187051df0330c77b7814f3a14570d37 /youtube_dl | |
parent | 2a7c6befc16f72df5368cb4adccd1cd84fd432d7 (diff) |
[indavideo] Add support for generic embeds (closes #11989)
Diffstat (limited to 'youtube_dl')
-rw-r--r-- | youtube_dl/extractor/extractors.py | 5 | ||||
-rw-r--r-- | youtube_dl/extractor/generic.py | 24 | ||||
-rw-r--r-- | youtube_dl/extractor/indavideo.py | 70 |
3 files changed, 41 insertions, 58 deletions
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 374aa185c..c9b49a0cd 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -469,10 +469,7 @@ from .imgur import ( ) from .ina import InaIE from .inc import IncIE -from .indavideo import ( - IndavideoIE, - IndavideoEmbedIE, -) +from .indavideo import IndavideoEmbedIE from .infoq import InfoQIE from .instagram import InstagramIE, InstagramUserIE from .internazionale import InternazionaleIE diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 47ac139c9..0292e0458 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -109,6 +109,7 @@ from .vice import ViceIE from .xfileshare import XFileShareIE from .cloudflarestream import CloudflareStreamIE from .peertube import PeerTubeIE +from .indavideo import IndavideoEmbedIE class GenericIE(InfoExtractor): @@ -2023,6 +2024,24 @@ class GenericIE(InfoExtractor): 'playlist_count': 2, }, { + # Indavideo embed + 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/', + 'info_dict': { + 'id': '1693903', + 'ext': 'mp4', + 'title': 'Így kell otthon hamburgert sütni', + 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7', + 'timestamp': 1426330212, + 'upload_date': '20150314', + 'uploader': 'StreetKitchen', + 'uploader_id': '546363', + }, + 'add_ie': [IndavideoEmbedIE.ie_key()], + 'params': { + 'skip_download': True, + }, + }, + { 'url': 'http://share-videos.se/auto/video/83645793?uid=13', 'md5': 'b68d276de422ab07ee1d49388103f457', 'info_dict': { @@ -3044,6 +3063,11 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key()) + indavideo_urls = IndavideoEmbedIE._extract_urls(webpage) + if indavideo_urls: + return self.playlist_from_matches( + indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key()) + sharevideos_urls = [mobj.group('url') for mobj in re.finditer( r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1', webpage)] diff --git a/youtube_dl/extractor/indavideo.py b/youtube_dl/extractor/indavideo.py index 2946c7b84..2b5b2b5b0 100644 --- a/youtube_dl/extractor/indavideo.py +++ b/youtube_dl/extractor/indavideo.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..compat import compat_str from ..utils import ( @@ -38,6 +40,20 @@ class IndavideoEmbedIE(InfoExtractor): 'only_matching': True, }] + # Some example URLs covered by generic extractor: + # http://indavideo.hu/video/Vicces_cica_1 + # http://index.indavideo.hu/video/2015_0728_beregszasz + # http://auto.indavideo.hu/video/Sajat_utanfutoban_a_kis_tacsko + # http://erotika.indavideo.hu/video/Amator_tini_punci + # http://film.indavideo.hu/video/f_hrom_nagymamm_volt + # http://palyazat.indavideo.hu/video/Embertelen_dal_Dodgem_egyuttes + + @staticmethod + def _extract_urls(webpage): + return re.findall( + r'<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//embed\.indavideo\.hu/player/video/[\da-f]+)', + webpage) + def _real_extract(self, url): video_id = self._match_id(url) @@ -110,57 +126,3 @@ class IndavideoEmbedIE(InfoExtractor): 'tags': tags, 'formats': formats, } - - -class IndavideoIE(InfoExtractor): - _VALID_URL = r'https?://(?:.+?\.)?indavideo\.hu/video/(?P<id>[^/#?]+)' - _TESTS = [{ - 'url': 'http://indavideo.hu/video/Vicces_cica_1', - 'md5': '8c82244ba85d2a2310275b318eb51eac', - 'info_dict': { - 'id': '1335611', - 'display_id': 'Vicces_cica_1', - 'ext': 'mp4', - 'title': 'Vicces cica', - 'description': 'Játszik a tablettel. :D', - 'thumbnail': r're:^https?://.*\.jpg$', - 'uploader': 'Jet_Pack', - 'uploader_id': '491217', - 'timestamp': 1390821212, - 'upload_date': '20140127', - 'duration': 7, - 'age_limit': 0, - 'tags': list, - }, - }, { - 'url': 'http://index.indavideo.hu/video/2015_0728_beregszasz', - 'only_matching': True, - }, { - 'url': 'http://auto.indavideo.hu/video/Sajat_utanfutoban_a_kis_tacsko', - 'only_matching': True, - }, { - 'url': 'http://erotika.indavideo.hu/video/Amator_tini_punci', - 'only_matching': True, - }, { - 'url': 'http://film.indavideo.hu/video/f_hrom_nagymamm_volt', - 'only_matching': True, - }, { - 'url': 'http://palyazat.indavideo.hu/video/Embertelen_dal_Dodgem_egyuttes', - 'only_matching': True, - }] - - def _real_extract(self, url): - display_id = self._match_id(url) - - webpage = self._download_webpage(url, display_id) - embed_url = self._search_regex( - (r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//embed\.indavideo\.hu/player/video/.+?)\1', - r'<link[^>]+rel="video_src"[^>]+href="(?P<url>.+?)"'), - webpage, 'embed url', group='url') - - return { - '_type': 'url_transparent', - 'ie_key': 'IndavideoEmbed', - 'url': embed_url, - 'display_id': display_id, - } |