github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[veehd] Send requests twice (Fixes #2102)

Browse source
This commit is contained in:
Philipp Hagemeister 2014-01-06 12:54:01 +01:00
parent 796495886e
commit c11a0611d9
1 changed files with 24 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

39
youtube_dl/extractor/veehd.py
View file

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import re import re
import json import json
@ -8,16 +10,17 @@
clean_html, clean_html,
) )
class VeeHDIE(InfoExtractor): class VeeHDIE(InfoExtractor):
_VALID_URL = r'https?://veehd\.com/video/(?P<id>\d+)' _VALID_URL = r'https?://veehd\.com/video/(?P<id>\d+)'
_TEST = { _TEST = {
u'url': u'http://veehd.com/video/4686958', 'url': 'http://veehd.com/video/4686958',
u'file': u'4686958.mp4', 'file': '4686958.mp4',
u'info_dict': { 'info_dict': {
u'title': u'Time Lapse View from Space ( ISS)', 'title': 'Time Lapse View from Space ( ISS)',
u'uploader_id': u'spotted', 'uploader_id': 'spotted',
u'description': u'md5:f0094c4cf3a72e22bc4e4239ef767ad7', 'description': 'md5:f0094c4cf3a72e22bc4e4239ef767ad7',
}, },
} }
@ -25,24 +28,30 @@ def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') 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) webpage = self._download_webpage(url, video_id)
player_path = self._search_regex(r'\$\("#playeriframe"\).attr\({src : "(.+?)"', player_path = self._search_regex(
webpage, u'player path') r'\$\("#playeriframe"\).attr\({src : "(.+?)"',
webpage, 'player path')
player_url = compat_urlparse.urljoin(url, player_path) player_url = compat_urlparse.urljoin(url, player_path)
player_page = self._download_webpage(player_url, video_id,
u'Downloading player page') self._download_webpage(player_url, video_id, 'Requesting player page')
config_json = self._search_regex(r'value=\'config=({.+?})\'', player_page = self._download_webpage(
player_page, u'config json') player_url, video_id, 'Downloading player page')
config_json = self._search_regex(
r'value=\'config=({.+?})\'', player_page, 'config json')
config = json.loads(config_json) config = json.loads(config_json)
video_url = compat_urlparse.unquote(config['clip']['url']) video_url = compat_urlparse.unquote(config['clip']['url'])
title = clean_html(get_element_by_id('videoName', webpage).rpartition('|')[0]) title = clean_html(get_element_by_id('videoName', webpage).rpartition('|')[0])
uploader_id = self._html_search_regex(r'<a href="/profile/\d+">(.+?)</a>', uploader_id = self._html_search_regex(r'<a href="/profile/\d+">(.+?)</a>',
webpage, u'uploader') webpage, 'uploader')
thumbnail = self._search_regex(r'<img id="veehdpreview" src="(.+?)"', thumbnail = self._search_regex(r'<img id="veehdpreview" src="(.+?)"',
webpage, u'thumbnail') webpage, 'thumbnail')
description = self._html_search_regex(r'<td class="infodropdown".*?<div>(.*?)<ul', description = self._html_search_regex(r'<td class="infodropdown".*?<div>(.*?)<ul',
webpage, u'description', flags=re.DOTALL) webpage, 'description', flags=re.DOTALL)
return { return {
'_type': 'video', '_type': 'video',