mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-08-25 08:41:48 +02:00
Add an extractor for VeeHD (closes #1359)
This commit is contained in:
parent
6c758d79de
commit
8e4e89f1c2
@ -89,6 +89,7 @@
|
||||
from .unistra import UnistraIE
|
||||
from .ustream import UstreamIE
|
||||
from .vbox7 import Vbox7IE
|
||||
from .veehd import VeeHDIE
|
||||
from .veoh import VeohIE
|
||||
from .vevo import VevoIE
|
||||
from .videofyme import VideofyMeIE
|
||||
|
56
youtube_dl/extractor/veehd.py
Normal file
56
youtube_dl/extractor/veehd.py
Normal file
@ -0,0 +1,56 @@
|
||||
import re
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
compat_urlparse,
|
||||
get_element_by_id,
|
||||
clean_html,
|
||||
)
|
||||
|
||||
class VeeHDIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://veehd.com/video/(?P<id>\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',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
player_path = self._search_regex(r'\$\("#playeriframe"\).attr\({src : "(.+?)"',
|
||||
webpage, u'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')
|
||||
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'<a href="/profile/\d+">(.+?)</a>',
|
||||
webpage, u'uploader')
|
||||
thumbnail = self._search_regex(r'<img id="veehdpreview" src="(.+?)"',
|
||||
webpage, u'thumbnail')
|
||||
description = self._html_search_regex(r'<td class="infodropdown".*?<div>(.*?)<ul',
|
||||
webpage, u'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,
|
||||
}
|
Loading…
Reference in New Issue
Block a user