X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fchirbit.py;h=b1eeaf101dda3a4a962862fa854db97ae1809329;hb=46bc9b7d7cea2e161670e65abe42ef01d39e8957;hp=06a3e1a7a7fc148778ba374a88087f8ab620270c;hpb=5da6bd00837236cf8a5dc5aeeadae5cfed7f2021;p=youtube-dl

diff --git a/youtube_dl/extractor/chirbit.py b/youtube_dl/extractor/chirbit.py
index 06a3e1a7a..b1eeaf101 100644
--- a/youtube_dl/extractor/chirbit.py
+++ b/youtube_dl/extractor/chirbit.py
@@ -2,33 +2,83 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    int_or_none,
+)
 
 
 class ChirbitIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?chirb\.it/(?P<id>[^/]+)'
-    _TEST = {
+    IE_NAME = 'chirbit'
+    _VALID_URL = r'https?://(?:www\.)?chirb\.it/(?:(?:wp|pl)/|fb_chirbit_player\.swf\?key=)?(?P<id>[\da-zA-Z]+)'
+    _TESTS = [{
         'url': 'http://chirb.it/PrIPv5',
         'md5': '9847b0dad6ac3e074568bf2cfb197de8',
         'info_dict': {
             'id': 'PrIPv5',
-            'display_id': 'kukushtv_1423231243',
             'ext': 'mp3',
             'title': 'Фасадстрой',
-            'url': 'http://audio.chirbit.com/kukushtv_1423231243.mp3'
+            'duration': 52,
+            'view_count': int,
+            'comment_count': int,
         }
-    }
+    }, {
+        'url': 'https://chirb.it/fb_chirbit_player.swf?key=PrIPv5',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        audio_linkid = self._match_id(url)
-        webpage = self._download_webpage(url, audio_linkid)
+        audio_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            'http://chirb.it/%s' % audio_id, audio_id)
+
+        audio_url = self._search_regex(
+            r'"setFile"\s*,\s*"([^"]+)"', webpage, 'audio url')
 
-        audio_title = self._html_search_regex(r'<h2\s+itemprop="name">(.*?)</h2>', webpage, 'title')
-        audio_id = self._html_search_regex(r'\("setFile",\s+"http://audio.chirbit.com/(.*?).mp3"\)', webpage, 'audio ID')
-        audio_url = 'http://audio.chirbit.com/' + audio_id + '.mp3';
+        title = self._search_regex(
+            r'itemprop="name">([^<]+)', webpage, 'title')
+        duration = parse_duration(self._html_search_meta(
+            'duration', webpage, 'duration', fatal=False))
+        view_count = int_or_none(self._search_regex(
+            r'itemprop="playCount"\s*>(\d+)', webpage,
+            'listen count', fatal=False))
+        comment_count = int_or_none(self._search_regex(
+            r'>(\d+) Comments?:', webpage,
+            'comment count', fatal=False))
 
         return {
-            'id': audio_linkid,
-            'display_id': audio_id,
-            'title': audio_title,
-            'url': audio_url
+            'id': audio_id,
+            'url': audio_url,
+            'title': title,
+            'duration': duration,
+            'view_count': view_count,
+            'comment_count': comment_count,
         }
+
+
+class ChirbitProfileIE(InfoExtractor):
+    IE_NAME = 'chirbit:profile'
+    _VALID_URL = r'https?://(?:www\.)?chirbit.com/(?:rss/)?(?P<id>[^/]+)'
+    _TEST = {
+        'url': 'http://chirbit.com/ScarletBeauty',
+        'info_dict': {
+            'id': 'ScarletBeauty',
+            'title': 'Chirbits by ScarletBeauty',
+        },
+        'playlist_mincount': 3,
+    }
+
+    def _real_extract(self, url):
+        profile_id = self._match_id(url)
+
+        rss = self._download_xml(
+            'http://chirbit.com/rss/%s' % profile_id, profile_id)
+
+        entries = [
+            self.url_result(audio_url.text, 'Chirbit')
+            for audio_url in rss.findall('./channel/item/link')]
+
+        title = rss.find('./channel/title').text
+
+        return self.playlist_result(entries, profile_id, title)