aboutsummaryrefslogtreecommitdiffhomepage
path: root/youtube_dl/extractor/megaphone.py
diff options
context:
space:
mode:
authorFilippo Valsorda <[email protected]>2018-01-07 15:03:28 +0100
committerGitHub <[email protected]>2018-01-07 15:03:28 +0100
commit97bc05116e15df3cf1b7b7216c60fad7ee0acc9f (patch)
tree453059413184d22a44241d251a82196c5d2461eb /youtube_dl/extractor/megaphone.py
parent7608a91ee7b40c74a35c30b44731606382702592 (diff)
parent0a5b1295b7c1aa6395b65ee137087c540b37b32b (diff)
downloadyoutube-dl-97bc05116e15df3cf1b7b7216c60fad7ee0acc9f.tar.gz
youtube-dl-97bc05116e15df3cf1b7b7216c60fad7ee0acc9f.zip
Merge branch 'master' into totalwebcastingtotalwebcasting
Diffstat (limited to 'youtube_dl/extractor/megaphone.py')
-rw-r--r--youtube_dl/extractor/megaphone.py55
1 files changed, 55 insertions, 0 deletions
diff --git a/youtube_dl/extractor/megaphone.py b/youtube_dl/extractor/megaphone.py
new file mode 100644
index 000000000..5bafa6cf4
--- /dev/null
+++ b/youtube_dl/extractor/megaphone.py
@@ -0,0 +1,55 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import js_to_json
+
+
+class MegaphoneIE(InfoExtractor):
+ IE_NAME = 'megaphone.fm'
+ IE_DESC = 'megaphone.fm embedded players'
+ _VALID_URL = r'https://player\.megaphone\.fm/(?P<id>[A-Z0-9]+)'
+ _TEST = {
+ 'url': 'https://player.megaphone.fm/GLT9749789991?"',
+ 'md5': '4816a0de523eb3e972dc0dda2c191f96',
+ 'info_dict': {
+ 'id': 'GLT9749789991',
+ 'ext': 'mp3',
+ 'title': '#97 What Kind Of Idiot Gets Phished?',
+ 'thumbnail': r're:^https://.*\.png.*$',
+ 'duration': 1776.26375,
+ 'author': 'Reply All',
+ },
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+
+ title = self._og_search_property('audio:title', webpage)
+ author = self._og_search_property('audio:artist', webpage)
+ thumbnail = self._og_search_thumbnail(webpage)
+
+ episode_json = self._search_regex(r'(?s)var\s+episode\s*=\s*(\{.+?\});', webpage, 'episode JSON')
+ episode_data = self._parse_json(episode_json, video_id, js_to_json)
+ video_url = self._proto_relative_url(episode_data['mediaUrl'], 'https:')
+
+ formats = [{
+ 'url': video_url,
+ }]
+
+ return {
+ 'id': video_id,
+ 'thumbnail': thumbnail,
+ 'title': title,
+ 'author': author,
+ 'duration': episode_data['duration'],
+ 'formats': formats,
+ }
+
+ @classmethod
+ def _extract_urls(cls, webpage):
+ return [m[0] for m in re.findall(
+ r'<iframe[^>]*?\ssrc=["\'](%s)' % cls._VALID_URL, webpage)]