1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-15 10:05:24 +01:00
yt-dlp/youtube_dl/extractor/primesharetv.py
2015-03-17 21:06:38 +06:00

70 lines
2.0 KiB
Python

from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
from ..utils import ExtractorError
class PrimeShareTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?primeshare\.tv/download/(?P<id>[\da-zA-Z]+)'
_TEST = {
'url': 'http://primeshare.tv/download/238790B611',
'md5': 'b92d9bf5461137c36228009f31533fbc',
'info_dict': {
'id': '238790B611',
'ext': 'mp4',
'title': 'Public Domain - 1960s Commercial - Crest Toothpaste-YKsuFona',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
if '>File not exist<' in webpage:
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
fields = dict(re.findall(r'''(?x)<input\s+
type="hidden"\s+
name="([^"]+)"\s+
(?:id="[^"]+"\s+)?
value="([^"]*)"
''', webpage))
headers = {
'Referer': url,
'Content-Type': 'application/x-www-form-urlencoded',
}
wait_time = int(self._search_regex(
r'var\s+cWaitTime\s*=\s*(\d+)',
webpage, 'wait time', default=7)) + 1
self._sleep(wait_time, video_id)
req = compat_urllib_request.Request(
url, compat_urllib_parse.urlencode(fields), headers)
video_page = self._download_webpage(
req, video_id, 'Downloading video page')
video_url = self._search_regex(
r"url\s*:\s*'([^']+\.primeshare\.tv(?::443)?/file/[^']+)'",
video_page, 'video url')
title = self._html_search_regex(
r'<h1>Watch\s*(?:&nbsp;)?\s*\((.+?)(?:\s*\[\.\.\.\])?\)\s*(?:&nbsp;)?\s*<strong>',
video_page, 'title')
return {
'id': video_id,
'url': video_url,
'title': title,
'ext': 'mp4',
}