commit 9d1b213845f35af4de40dd057754f8f285091bfa
parent 548482841867a16d3f68e18f78091e59f768a880
Author: Sergey M․ <dstftw@gmail.com>
Date:   Mon, 30 Jul 2018 03:05:36 +0700

[viqeo] Add extractor (closes #17066)

Diffstat:
Myoutube_dl/extractor/extractors.py | 1+
Myoutube_dl/extractor/generic.py | 15+++++++++++++++
Ayoutube_dl/extractor/viqeo.py | 99+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 115 insertions(+), 0 deletions(-)

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py @@ -1291,6 +1291,7 @@ from .viki import ( VikiIE, VikiChannelIE, ) +from .viqeo import ViqeoIE from .viu import ( ViuIE, ViuPlaylistIE, diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py @@ -113,6 +113,7 @@ from .peertube import PeerTubeIE from .indavideo import IndavideoEmbedIE from .apa import APAIE from .foxnews import FoxNewsIE +from .viqeo import ViqeoIE class GenericIE(InfoExtractor): @@ -2060,6 +2061,15 @@ class GenericIE(InfoExtractor): }, 'skip': 'TODO: fix nested playlists processing in tests', }, + { + # Viqeo embeds + 'url': 'https://viqeo.tv/', + 'info_dict': { + 'id': 'viqeo', + 'title': 'All-new video platform', + }, + 'playlist_count': 6, + }, # { # # TODO: find another test # # http://schema.org/VideoObject @@ -3094,6 +3104,11 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( sharevideos_urls, video_id, video_title) + viqeo_urls = ViqeoIE._extract_urls(webpage) + if viqeo_urls: + return self.playlist_from_matches( + viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key()) + # Look for HTML5 media entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls') if entries: diff --git a/youtube_dl/extractor/viqeo.py b/youtube_dl/extractor/viqeo.py @@ -0,0 +1,99 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + str_or_none, + url_or_none, +) + + +class ViqeoIE(InfoExtractor): + _VALID_URL = r'''(?x) + (?: + viqeo:| + https?://cdn\.viqeo\.tv/embed/*\?.*?\bvid=| + https?://api\.viqeo\.tv/v\d+/data/startup?.*?\bvideo(?:%5B%5D|\[\])= + ) + (?P<id>[\da-f]+) + ''' + _TESTS = [{ + 'url': 'https://cdn.viqeo.tv/embed/?vid=cde96f09d25f39bee837', + 'md5': 'a169dd1a6426b350dca4296226f21e76', + 'info_dict': { + 'id': 'cde96f09d25f39bee837', + 'ext': 'mp4', + 'title': 'cde96f09d25f39bee837', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 76, + }, + }, { + 'url': 'viqeo:cde96f09d25f39bee837', + 'only_matching': True, + }, { + 'url': 'https://api.viqeo.tv/v1/data/startup?video%5B%5D=71bbec412ade45c3216c&profile=112', + 'only_matching': True, + }] + + @staticmethod + def _extract_urls(webpage): + return [ + mobj.group('url') + for mobj in re.finditer( + r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//cdn\.viqeo\.tv/embed/*\?.*?\bvid=[\da-f]+.*?)\1', + webpage)] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage( + 'https://cdn.viqeo.tv/embed/?vid=%s' % video_id, video_id) + + data = self._parse_json( + self._search_regex( + r'SLOT_DATA\s*=\s*({.+?})\s*;', webpage, 'slot data'), + video_id) + + formats = [] + thumbnails = [] + for media_file in data['mediaFiles']: + if not isinstance(media_file, dict): + continue + media_url = url_or_none(media_file.get('url')) + if not media_url or not media_url.startswith(('http', '//')): + continue + media_type = str_or_none(media_file.get('type')) + if not media_type: + continue + media_kind = media_type.split('/')[0].lower() + f = { + 'url': media_url, + 'width': int_or_none(media_file.get('width')), + 'height': int_or_none(media_file.get('height')), + } + format_id = str_or_none(media_file.get('quality')) + if media_kind == 'image': + f['id'] = format_id + thumbnails.append(f) + elif media_kind in ('video', 'audio'): + is_audio = media_kind == 'audio' + f.update({ + 'format_id': 'audio' if is_audio else format_id, + 'fps': int_or_none(media_file.get('fps')), + 'vcodec': 'none' if is_audio else None, + }) + formats.append(f) + self._sort_formats(formats) + + duration = int_or_none(data.get('duration')) + + return { + 'id': video_id, + 'title': video_id, + 'duration': duration, + 'thumbnails': thumbnails, + 'formats': formats, + }