1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
youtube-dl/youtube_dl/extractor/veehd.py

90 lines
3 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..compat import (
compat_urlparse,
)
from ..utils import (
2015-01-11 09:42:53 +00:00
ExtractorError,
clean_html,
get_element_by_id,
)
class VeeHDIE(InfoExtractor):
_VALID_URL = r'https?://veehd\.com/video/(?P<id>\d+)'
_TEST = {
2015-01-11 10:20:39 +00:00
'url': 'http://veehd.com/video/4639434_Solar-Sinter',
'info_dict': {
2015-01-11 10:20:39 +00:00
'id': '4639434',
2014-08-27 23:37:57 +00:00
'ext': 'mp4',
2015-01-11 10:20:39 +00:00
'title': 'Solar Sinter',
'uploader_id': 'VideoEyes',
'description': 'md5:46a840e8692ddbaffb5f81d9885cb457',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
# 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)
2015-01-11 09:42:53 +00:00
if 'This video has been removed<' in webpage:
raise ExtractorError('Video %s has been removed' % video_id, expected=True)
player_path = self._search_regex(
r'\$\("#playeriframe"\).attr\({src : "(.+?)"',
webpage, 'player path')
player_url = compat_urlparse.urljoin(url, player_path)
self._download_webpage(player_url, video_id, 'Requesting player page')
player_page = self._download_webpage(
player_url, video_id, 'Downloading player page')
2015-01-11 10:20:16 +00:00
config_json = self._search_regex(
2015-01-11 10:20:16 +00:00
r'value=\'config=({.+?})\'', player_page, 'config json', default=None)
if config_json:
config = json.loads(config_json)
video_url = compat_urlparse.unquote(config['clip']['url'])
else:
iframe_src = self._search_regex(
r'<iframe[^>]+src="/?([^"]+)"', player_page, 'iframe url')
iframe_url = 'http://veehd.com/%s' % iframe_src
self._download_webpage(iframe_url, video_id, 'Requesting iframe page')
iframe_page = self._download_webpage(
iframe_url, video_id, 'Downloading iframe page')
video_url = self._search_regex(
r"file\s*:\s*'([^']+)'", iframe_page, 'video url')
title = clean_html(get_element_by_id('videoName', webpage).rpartition('|')[0])
2015-01-11 10:20:16 +00:00
uploader_id = self._html_search_regex(
r'<a href="/profile/\d+">(.+?)</a>',
webpage, 'uploader')
thumbnail = self._search_regex(
r'<img id="veehdpreview" src="(.+?)"',
webpage, 'thumbnail')
description = self._html_search_regex(
r'<td class="infodropdown".*?<div>(.*?)<ul',
webpage, 'description', flags=re.DOTALL)
return {
'_type': 'video',
'id': video_id,
'title': title,
'url': video_url,
'ext': 'mp4',
'uploader_id': uploader_id,
'thumbnail': thumbnail,
'description': description,
}