[promptfile] Add new extractor

This commit is contained in:
Naglis Jonaitis 2014-08-29 00:20:10 +03:00
parent 863f08a92e
commit 8e72edfb19
2 changed files with 68 additions and 0 deletions

View File

@ -257,6 +257,7 @@ from .podomatic import PodomaticIE
from .pornhd import PornHdIE from .pornhd import PornHdIE
from .pornhub import PornHubIE from .pornhub import PornHubIE
from .pornotube import PornotubeIE from .pornotube import PornotubeIE
from .promptfile import PromptFileIE
from .prosiebensat1 import ProSiebenSat1IE from .prosiebensat1 import ProSiebenSat1IE
from .pyvideo import PyvideoIE from .pyvideo import PyvideoIE
from .radiofrance import RadioFranceIE from .radiofrance import RadioFranceIE

View File

@ -0,0 +1,67 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
determine_ext,
compat_urllib_parse,
compat_urllib_request,
)
class PromptFileIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P<id>[0-9A-Z\-]+)'
_FILE_NOT_FOUND_REGEX = r'<div.+id="not_found_msg".+>.+</div>[^-]'
_TEST = {
'url': 'http://www.promptfile.com/l/D21B4746E9-F01462F0FF',
'md5': 'd1451b6302da7215485837aaea882c4c',
'info_dict': {
'id': 'D21B4746E9-F01462F0FF',
'ext': 'mp4',
'title': 'Birds.mp4',
'thumbnail': 're:^https?://.*\.jpg$',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
raise ExtractorError('Video %s does not exist' % video_id,
expected=True)
fields = dict(re.findall(r'''(?x)type="hidden"\s+
name="(.+?)"\s+
value="(.*?)"
''', webpage))
post = compat_urllib_parse.urlencode(fields)
req = compat_urllib_request.Request(url, post)
req.add_header('Content-type', 'application/x-www-form-urlencoded')
webpage = self._download_webpage(
req, video_id, 'Downloading video page')
url = self._html_search_regex(r'url:\s*\'([^\']+)\'', webpage, 'URL')
title = self._html_search_regex(
r'<span.+title="([^"]+)">', webpage, 'title')
thumbnail = self._html_search_regex(
r'<div id="player_overlay">.*button>.*?<img src="([^"]+)"',
webpage, 'thumbnail', fatal=False, flags=re.DOTALL)
formats = [{
'format_id': 'sd',
'url': url,
'ext': determine_ext(title),
'quality': 1,
}]
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'formats': formats,
}