1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-09 12:42:28 +01:00
yt-dlp/youtube_dl/extractor/motorsport.py
Philipp Hagemeister 1cc79574fc Fix imports and general cleanup
· Import from compat what comes from compat. Yes, some names are available in utils too, but that's an implementation detail.
· Use _match_id consistently whenever possible
· Fix some outdated tests
· Use consistent valid URL (always match the whole protocol, no ^ at start required)
· Use modern test definitions
2014-12-13 12:35:45 +01:00

64 lines
2.2 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# coding: utf-8
from __future__ import unicode_literals
import hashlib
import json
import time
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_str,
)
from ..utils import (
int_or_none,
)
class MotorsportIE(InfoExtractor):
IE_DESC = 'motorsport.com'
_VALID_URL = r'http://www\.motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/(?:$|[?#])'
_TEST = {
'url': 'http://www.motorsport.com/f1/video/main-gallery/red-bull-racing-2014-rules-explained/',
'md5': '5592cb7c5005d9b2c163df5ac3dc04e4',
'info_dict': {
'id': '7063',
'ext': 'mp4',
'title': 'Red Bull Racing: 2014 Rules Explained',
'duration': 207,
'description': 'A new clip from Red Bull sees Daniel Ricciardo and Sebastian Vettel explain the 2014 Formula One regulations which are arguably the most complex the sport has ever seen.',
'uploader': 'rainiere',
'thumbnail': r're:^http://.*motorsport\.com/.+\.jpg$'
}
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
flashvars_code = self._html_search_regex(
r'<embed id="player".*?flashvars="([^"]+)"', webpage, 'flashvars')
flashvars = compat_parse_qs(flashvars_code)
params = json.loads(flashvars['parameters'][0])
e = compat_str(int(time.time()) + 24 * 60 * 60)
base_video_url = params['location'] + '?e=' + e
s = 'h3hg713fh32'
h = hashlib.md5((s + base_video_url).encode('utf-8')).hexdigest()
video_url = base_video_url + '&h=' + h
uploader = self._html_search_regex(
r'(?s)<span class="label">Video by: </span>(.*?)</a>', webpage,
'uploader', fatal=False)
return {
'id': params['video_id'],
'display_id': display_id,
'title': params['title'],
'url': video_url,
'description': params.get('description'),
'thumbnail': params.get('main_thumb'),
'duration': int_or_none(params.get('duration')),
'uploader': uploader,
}