[megaphone] Add extractor

youtube_dl/extractor/extractors.py

@@ -558,6 +558,7 @@ from .matchtv import MatchTVIE
 from .mdr import MDRIE
 from .mediaset import MediasetIE
 from .medici import MediciIE
+from .megaphone import MegaphoneIE
 from .meipai import MeipaiIE
 from .melonvod import MelonVODIE
 from .meta import METAIE

youtube_dl/extractor/generic.py

@@ -97,6 +97,7 @@ from .washingtonpost import WashingtonPostIE
 from .wistia import WistiaIE
 from .mediaset import MediasetIE
 from .joj import JojIE
+from .megaphone import MegaphoneIE
 
 
 class GenericIE(InfoExtractor):
@@ -2790,6 +2791,13 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 joj_urls, video_id, video_title, ie=JojIE.ie_key())
 
+        # Look for megaphone.fm embeds
+        mpfn_urls = MegaphoneIE._extract_urls(webpage)
+        if mpfn_urls:
+            return self.playlist_from_matches(
+                mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
+
+
         def merge_dicts(dict1, dict2):
             merged = {}
             for k, v in dict1.items():

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': '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)]