From c11a0611d909a4c7dce7bdda1d146517de8d55b2 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 6 Jan 2014 12:54:01 +0100 Subject: [PATCH] [veehd] Send requests twice (Fixes #2102) --- youtube_dl/extractor/veehd.py | 39 +++++++++++++++++++++-------------- 1 file changed, 24 insertions(+), 15 deletions(-) diff --git a/youtube_dl/extractor/veehd.py b/youtube_dl/extractor/veehd.py index 3cf8c853d2..b1c854a646 100644 --- a/youtube_dl/extractor/veehd.py +++ b/youtube_dl/extractor/veehd.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re import json @@ -8,16 +10,17 @@ from ..utils import ( clean_html, ) + class VeeHDIE(InfoExtractor): _VALID_URL = r'https?://veehd\.com/video/(?P\d+)' _TEST = { - u'url': u'http://veehd.com/video/4686958', - u'file': u'4686958.mp4', - u'info_dict': { - u'title': u'Time Lapse View from Space ( ISS)', - u'uploader_id': u'spotted', - u'description': u'md5:f0094c4cf3a72e22bc4e4239ef767ad7', + 'url': 'http://veehd.com/video/4686958', + 'file': '4686958.mp4', + 'info_dict': { + 'title': 'Time Lapse View from Space ( ISS)', + 'uploader_id': 'spotted', + 'description': 'md5:f0094c4cf3a72e22bc4e4239ef767ad7', }, } @@ -25,24 +28,30 @@ class VeeHDIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + # VeeHD seems to send garbage on the first request. + # See https://github.com/rg3/youtube-dl/issues/2102 + self._download_webpage(url, video_id, 'Requesting webpage') webpage = self._download_webpage(url, video_id) - player_path = self._search_regex(r'\$\("#playeriframe"\).attr\({src : "(.+?)"', - webpage, u'player path') + player_path = self._search_regex( + r'\$\("#playeriframe"\).attr\({src : "(.+?)"', + webpage, 'player path') player_url = compat_urlparse.urljoin(url, player_path) - player_page = self._download_webpage(player_url, video_id, - u'Downloading player page') - config_json = self._search_regex(r'value=\'config=({.+?})\'', - player_page, u'config json') + + self._download_webpage(player_url, video_id, 'Requesting player page') + player_page = self._download_webpage( + player_url, video_id, 'Downloading player page') + config_json = self._search_regex( + r'value=\'config=({.+?})\'', player_page, 'config json') config = json.loads(config_json) video_url = compat_urlparse.unquote(config['clip']['url']) title = clean_html(get_element_by_id('videoName', webpage).rpartition('|')[0]) uploader_id = self._html_search_regex(r'(.+?)', - webpage, u'uploader') + webpage, 'uploader') thumbnail = self._search_regex(r'(.*?)