From e648b22dbd454236d03b474c8a9363d83a5065d7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Sat, 29 Jun 2013 14:43:35 +0200 Subject: [PATCH] Add TF1IE --- youtube_dl/extractor/__init__.py | 2 +- youtube_dl/extractor/wat.py | 30 ++++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 65a23d52b..721eb9380 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -54,7 +54,7 @@ from .vbox7 import Vbox7IE from .vevo import VevoIE from .vimeo import VimeoIE from .vine import VineIE -from .wat import WatIE +from .wat import WatIE, TF1IE from .wimp import WimpIE from .worldstarhiphop import WorldStarHipHopIE from .xhamster import XHamsterIE diff --git a/youtube_dl/extractor/wat.py b/youtube_dl/extractor/wat.py index aba4159e9..723410542 100644 --- a/youtube_dl/extractor/wat.py +++ b/youtube_dl/extractor/wat.py @@ -1,3 +1,5 @@ +# coding: utf-8 + import json import re @@ -46,3 +48,31 @@ class WatIE(InfoExtractor): 'title': title, 'thumbnail': thumbnail, } + +class TF1IE(InfoExtractor): + """ + TF1 uses the wat.tv player, currently it can only download videos with the + html5 player enabled, it cannot download HD videos or the news. + """ + _VALID_URL = r'http://videos.tf1.fr/.*-(.*?).html' + _TEST = { + u'url': u'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html', + u'file': u'6bysb.mp4', + u'md5': u'66789d3e91278d332f75e1feb7aea327', + u'info_dict': { + u"title": u"Citroën Grand C4 Picasso 2013 : présentation officielle" + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + id = mobj.group(1) + webpage = self._download_webpage(url, id) + embed_url = self._html_search_regex(r'"(https://www.wat.tv/embedframe/.*?)"', + webpage, 'embed url') + embed_page = self._download_webpage(embed_url, id, u'Downloading embed player page') + wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id') + wat_info = self._download_webpage('http://www.wat.tv/interface/contentv3/%s' % wat_id, id, u'Downloading Wat info') + wat_info = json.loads(wat_info)['media'] + wat_url = wat_info['url'] + return self.url_result(wat_url, 'Wat')