mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-12-14 07:12:41 +00:00
[screencast] Add new extractor (Fixes #3236)
This commit is contained in:
parent
4e415288d7
commit
38ad119f97
2 changed files with 49 additions and 0 deletions
|
@ -248,6 +248,7 @@ from .rutube import (
|
|||
from .rutv import RUTVIE
|
||||
from .savefrom import SaveFromIE
|
||||
from .scivee import SciVeeIE
|
||||
from .screencast import ScreencastIE
|
||||
from .servingsys import ServingSysIE
|
||||
from .sina import SinaIE
|
||||
from .slideshare import SlideshareIE
|
||||
|
|
48
youtube_dl/extractor/screencast.py
Normal file
48
youtube_dl/extractor/screencast.py
Normal file
|
@ -0,0 +1,48 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
compat_parse_qs,
|
||||
compat_urllib_request,
|
||||
)
|
||||
|
||||
|
||||
class ScreencastIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.screencast\.com/t/(?P<id>[a-zA-Z0-9]+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.screencast.com/t/3ZEjQXlT',
|
||||
'md5': '917df1c13798a3e96211dd1561fded83',
|
||||
'info_dict': {
|
||||
'id': '3ZEjQXlT',
|
||||
'ext': 'm4v',
|
||||
'title': 'Color Measurement with Ocean Optics Spectrometers',
|
||||
'description': 'md5:240369cde69d8bed61349a199c5fb153',
|
||||
'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)
|
||||
|
||||
flash_vars_s = self._html_search_regex(
|
||||
r'<param name="flashVars" value="([^"]+)"', webpage, 'flash vars')
|
||||
flash_vars = compat_parse_qs(flash_vars_s)
|
||||
|
||||
thumbnail = flash_vars.get('thumb', [None])[0]
|
||||
video_url_raw = compat_urllib_request.quote(flash_vars['content'][0])
|
||||
video_url = video_url_raw.replace('http%3A', 'http:')
|
||||
title = self._og_search_title(webpage)
|
||||
description = self._og_search_description(webpage)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
}
|
Loading…
Reference in a new issue