From adf2c0989d6d525b3a691eb64651b3330f5a76fc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 12 Sep 2014 20:51:48 +0700 Subject: [PATCH] [telemb] Extract all formats and modernize --- youtube_dl/extractor/__init__.py | 2 +- youtube_dl/extractor/telemb.py | 93 ++++++++++++++++++++++---------- 2 files changed, 66 insertions(+), 29 deletions(-) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 94e370281..13b3616d3 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -345,7 +345,7 @@ from .teamcoco import TeamcocoIE from .techtalks import TechTalksIE from .ted import TEDIE -from .telemb import TelembIE +from .telemb import TeleMBIE from .tenplay import TenPlayIE from .testurl import TestURLIE from .tf1 import TF1IE diff --git a/youtube_dl/extractor/telemb.py b/youtube_dl/extractor/telemb.py index 383c26d96..cf5bb89b1 100644 --- a/youtube_dl/extractor/telemb.py +++ b/youtube_dl/extractor/telemb.py @@ -1,40 +1,77 @@ +# coding: utf-8 +from __future__ import unicode_literals + import re -# -*- coding: utf-8 -*- -# needed for the title french ê! coding utf-8- -*- -# based on the vine.co and lots of help from https://filippo.io/add-support-for-a-new-video-site-to-youtube-dl/ + from .common import InfoExtractor +from ..utils import remove_start -class TelembIE(InfoExtractor): - - _VALID_URL = r'https?://www\.telemb\.be/(?P.*)' - - _TEST = { - u'url': u'http://www.telemb.be/mons-cook-with-danielle-des-cours-de-cuisine-en-anglais-_d_13466.html', - u'file': u'mons-cook-with-danielle-des-cours-de-cuisine-en-anglais-_d_13466.html.mp4', - u'md5': u'f45ea69878516ba039835794e0f8f783', - u'info_dict': { - u"title": u'TéléMB : Mons - Cook with Danielle : des cours de cuisine en anglais ! - Les reportages' - } - } +class TeleMBIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?telemb\.be/(?P.+?)_d_(?P\d+)\.html' + _TESTS = [ + { + 'url': 'http://www.telemb.be/mons-cook-with-danielle-des-cours-de-cuisine-en-anglais-_d_13466.html', + 'md5': 'f45ea69878516ba039835794e0f8f783', + 'info_dict': { + 'id': '13466', + 'display_id': 'mons-cook-with-danielle-des-cours-de-cuisine-en-anglais-', + 'ext': 'mp4', + 'title': 'Mons - Cook with Danielle : des cours de cuisine en anglais ! - Les reportages', + 'description': 'md5:bc5225f47b17c309761c856ad4776265', + 'thumbnail': 're:^http://.*\.(?:jpg|png)$', + } + }, + { + 'url': 'http://telemb.be/les-reportages-havre-incendie-mortel_d_13514.html', + 'md5': '6e9682736e5ccd4eab7f21e855350733', + 'info_dict': { + 'id': '13514', + 'display_id': 'les-reportages-havre-incendie-mortel', + 'ext': 'mp4', + 'title': 'Havré - Incendie mortel - Les reportages', + 'description': 'md5:5e54cb449acb029c2b7734e2d946bd4a', + 'thumbnail': 're:^http://.*\.(?:jpg|png)$', + } + }, + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - webpage_url = 'http://www.telemb.be/' + video_id - webpage = self._download_webpage(webpage_url, video_id) + display_id = mobj.group('display_id') + webpage = self._download_webpage(url, display_id) - self.report_extraction(video_id) + formats = [] + for video_url in re.findall(r'file\s*:\s*"([^"]+)"', webpage): + fmt = { + 'url': video_url, + 'format_id': video_url.split(':')[0] + } + rtmp = re.search(r'^(?Prtmp://[^/]+/(?P.+))/(?Pmp4:.+)$', video_url) + if rtmp: + fmt.update({ + 'play_path': rtmp.group('playpath'), + 'app': rtmp.group('app'), + 'player_url': 'http://p.jwpcdn.com/6/10/jwplayer.flash.swf', + 'page_url': 'http://www.telemb.be', + 'preference': -1, + }) + formats.append(fmt) + self._sort_formats(formats) - video_url = self._html_search_regex(r'"(http://wowza\.imust\.org/srv/vod/.*\.mp4)"', - webpage, u'video URL') + title = remove_start(self._og_search_title(webpage), 'TéléMB : ') + description = self._html_search_regex( + r'', + webpage, 'description', fatal=False) + thumbnail = self._og_search_thumbnail(webpage) - return [{ - 'id': video_id, - 'url': video_url, - 'ext': 'mp4', - 'title': self._og_search_title(webpage), - 'thumbnail': self._og_search_thumbnail(webpage), - }] + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'formats': formats, + }