New upstream version 2019.01.16

[youtubedl] / youtube_dl / extractor / chirbit.py

diff --git a/youtube_dl/extractor/chirbit.py b/youtube_dl/extractor/chirbit.py
index b1eeaf101dda3a4a962862fa854db97ae1809329..8d75cdf199b7f7b8ac5321c1e58b7ef57d4f2622 100644 (file)
--- a/youtube_dl/extractor/chirbit.py
+++ b/youtube_dl/extractor/chirbit.py
@@ -1,30 +1,35 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
 # coding: utf-8
 from __future__ import unicode_literals
 

+import re
+

 from .common import InfoExtractor
 from .common import InfoExtractor

-from ..utils import (
-    parse_duration,
-    int_or_none,
-)
+from ..compat import compat_b64decode
+from ..utils import parse_duration

 
 
 class ChirbitIE(InfoExtractor):
     IE_NAME = 'chirbit'
     _VALID_URL = r'https?://(?:www\.)?chirb\.it/(?:(?:wp|pl)/|fb_chirbit_player\.swf\?key=)?(?P<id>[\da-zA-Z]+)'
     _TESTS = [{
 
 
 class ChirbitIE(InfoExtractor):
     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',
+        'url': 'http://chirb.it/be2abG',

         'info_dict': {
         'info_dict': {

-            'id': 'PrIPv5',
+            'id': 'be2abG',

             'ext': 'mp3',
             'ext': 'mp3',

-            'title': 'Фасадстрой',
-            'duration': 52,
-            'view_count': int,
-            'comment_count': int,
+            'title': 'md5:f542ea253f5255240be4da375c6a5d7e',
+            'description': 'md5:f24a4e22a71763e32da5fed59e47c770',
+            'duration': 306,
+            'uploader': 'Gerryaudio',
+        },
+        'params': {
+            'skip_download': True,

         }
     }, {
         'url': 'https://chirb.it/fb_chirbit_player.swf?key=PrIPv5',
         'only_matching': True,
         }
     }, {
         'url': 'https://chirb.it/fb_chirbit_player.swf?key=PrIPv5',
         'only_matching': True,

+    }, {
+        'url': 'https://chirb.it/wp/MN58c2',
+        'only_matching': True,

     }]
 
     def _real_extract(self, url):
     }]
 
     def _real_extract(self, url):


@@ -33,38 +38,43 @@ class ChirbitIE(InfoExtractor):
         webpage = self._download_webpage(
             'http://chirb.it/%s' % audio_id, audio_id)
 
         webpage = self._download_webpage(
             'http://chirb.it/%s' % audio_id, audio_id)
 

-        audio_url = self._search_regex(
-            r'"setFile"\s*,\s*"([^"]+)"', webpage, 'audio url')
+        data_fd = self._search_regex(
+            r'data-fd=(["\'])(?P<url>(?:(?!\1).)+)\1',
+            webpage, 'data fd', group='url')
+
+        # Reverse engineered from https://chirb.it/js/chirbit.player.js (look
+        # for soundURL)
+        audio_url = compat_b64decode(data_fd[::-1]).decode('utf-8')

 
         title = self._search_regex(
 
         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))
+            r'class=["\']chirbit-title["\'][^>]*>([^<]+)', webpage, 'title')
+        description = self._search_regex(
+            r'<h3>Description</h3>\s*<pre[^>]*>([^<]+)</pre>',
+            webpage, 'description', default=None)
+        duration = parse_duration(self._search_regex(
+            r'class=["\']c-length["\'][^>]*>([^<]+)',
+            webpage, 'duration', fatal=False))
+        uploader = self._search_regex(
+            r'id=["\']chirbit-username["\'][^>]*>([^<]+)',
+            webpage, 'uploader', fatal=False)

 
         return {
             'id': audio_id,
             'url': audio_url,
             'title': title,
 
         return {
             'id': audio_id,
             'url': audio_url,
             'title': title,

+            'description': description,

             'duration': duration,
             'duration': duration,

-            'view_count': view_count,
-            'comment_count': comment_count,
+            'uploader': uploader,

         }
 
 
 class ChirbitProfileIE(InfoExtractor):
     IE_NAME = 'chirbit:profile'
         }
 
 
 class ChirbitProfileIE(InfoExtractor):
     IE_NAME = 'chirbit:profile'

-    _VALID_URL = r'https?://(?:www\.)?chirbit.com/(?:rss/)?(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?chirbit\.com/(?:rss/)?(?P<id>[^/]+)'

     _TEST = {
         'url': 'http://chirbit.com/ScarletBeauty',
         'info_dict': {
             'id': 'ScarletBeauty',
     _TEST = {
         'url': 'http://chirbit.com/ScarletBeauty',
         'info_dict': {
             'id': 'ScarletBeauty',

-            'title': 'Chirbits by ScarletBeauty',

         },
         'playlist_mincount': 3,
     }
         },
         'playlist_mincount': 3,
     }


@@ -72,13 +82,10 @@ class ChirbitProfileIE(InfoExtractor):
     def _real_extract(self, url):
         profile_id = self._match_id(url)
 
     def _real_extract(self, url):
         profile_id = self._match_id(url)
 

-        rss = self._download_xml(
-            'http://chirbit.com/rss/%s' % profile_id, profile_id)
+        webpage = self._download_webpage(url, profile_id)

 
         entries = [
 
         entries = [

-            self.url_result(audio_url.text, 'Chirbit')
-            for audio_url in rss.findall('./channel/item/link')]
-
-        title = rss.find('./channel/title').text
+            self.url_result(self._proto_relative_url('//chirb.it/' + video_id))
+            for _, video_id in re.findall(r'<input[^>]+id=([\'"])copy-btn-(?P<id>[0-9a-zA-Z]+)\1', webpage)]

 
 

-        return self.playlist_result(entries, profile_id, title)
+        return self.playlist_result(entries, profile_id)