Browse Source

[stitcher] Add extractor

Stitcher review updates

Removed re import

Stitcher review updates
master
mjdubell 9 years ago
committed by Sergey M․
parent
commit
4211c83aa4
2 changed files with 38 additions and 0 deletions
  1. 1
      youtube_dl/extractor/__init__.py
  2. 37
      youtube_dl/extractor/stitcher.py

1
youtube_dl/extractor/__init__.py

@ -586,6 +586,7 @@ from .spankwire import SpankwireIE
from .spiegel import SpiegelIE, SpiegelArticleIE
from .spiegeltv import SpiegeltvIE
from .spike import SpikeIE
from .stitcher import StitcherIE
from .sport5 import Sport5IE
from .sportbox import (
SportBoxIE,

37
youtube_dl/extractor/stitcher.py

@ -0,0 +1,37 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import int_or_none
class StitcherIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?stitcher\.com/podcast/[\/a-z\-]+(?P<id>\d+)'
_TEST = {
'url': 'http://www.stitcher.com/podcast/the-talking-machines/e/40789481?autoplay=true',
'md5': '391dd4e021e6edeb7b8e68fbf2e9e940',
'info_dict': {
'id': '40789481',
'ext': 'mp3',
'title': 'Machine Learning Mastery and Cancer Clusters from Talking Machines',
}
}
def _real_extract(self, url):
audio_id = self._match_id(url)
webpage = self._download_webpage(url, audio_id)
title = self._og_search_title(webpage)
url = self._search_regex(r'episodeURL: "(.+?)"', webpage, 'url')
episode_image = self._search_regex(r'episodeImage: "(.+?)"', webpage, 'episode_image', fatal=False)
duration = int_or_none(self._search_regex(r'duration: (\d+?),', webpage, 'duration', fatal=False))
return {
'id': audio_id,
'url': url,
'title': title,
'duration': duration,
'thumbnail': episode_image,
'ext': 'mp3',
'vcodec': 'none',
}
Loading…
Cancel
Save