added new extractor from template

This commit is contained in:
Felix Dollack 2016-02-07 16:03:17 +01:00
parent 8411229bd5
commit 33c9af1858
2 changed files with 39 additions and 0 deletions

View File

@ -20,6 +20,7 @@ from .aftonbladet import AftonbladetIE
from .airmozilla import AirMozillaIE from .airmozilla import AirMozillaIE
from .aljazeera import AlJazeeraIE from .aljazeera import AlJazeeraIE
from .alphaporno import AlphaPornoIE from .alphaporno import AlphaPornoIE
from .animefullx import AnimefullxIE
from .anitube import AnitubeIE from .anitube import AnitubeIE
from .anysex import AnySexIE from .anysex import AnySexIE
from .aol import AolIE from .aol import AolIE

View File

@ -0,0 +1,38 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class AnimefullxIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://yourextractor.com/watch/42',
'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
'info_dict': {
'id': '42',
'ext': 'mp4',
'title': 'Video title goes here',
'thumbnail': 're:^https?://.*\.jpg$',
# TODO more properties, either as:
# * A value
# * MD5 checksum; start the string with md5:
# * A regular expression; start the string with re:
# * Any Python type (for example int or float)
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
# TODO more code goes here, for example ...
title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
return {
'id': video_id,
'title': title,
'description': self._og_search_description(webpage),
'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False),
# TODO more properties (see youtube_dl/extractor/common.py)
}