New upstream version 2019.09.28

[youtubedl] / youtube_dl / extractor / polskieradio.py

diff --git a/youtube_dl/extractor/polskieradio.py b/youtube_dl/extractor/polskieradio.py
index f559b899f44d216d0f59a5e282de0658cbf4af48..978d6f813b6d0a88aafb707aba40de092c926a44 100644 (file)
--- a/youtube_dl/extractor/polskieradio.py
+++ b/youtube_dl/extractor/polskieradio.py
@@ -1,14 +1,17 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
 # coding: utf-8
 from __future__ import unicode_literals
 

+import itertools

 import re
 
 from .common import InfoExtractor
 from ..compat import (
     compat_str,
     compat_urllib_parse_unquote,
 import re
 
 from .common import InfoExtractor
 from ..compat import (
     compat_str,
     compat_urllib_parse_unquote,

+    compat_urlparse

 )
 from ..utils import (
 )
 from ..utils import (

+    extract_attributes,

     int_or_none,
     strip_or_none,
     unified_timestamp,
     int_or_none,
     strip_or_none,
     unified_timestamp,


@@ -33,7 +36,7 @@ class PolskieRadioIE(InfoExtractor):
                 'timestamp': 1456594200,
                 'upload_date': '20160227',
                 'duration': 2364,
                 'timestamp': 1456594200,
                 'upload_date': '20160227',
                 'duration': 2364,

-                'thumbnail': 're:^https?://static\.prsa\.pl/images/.*\.jpg$'
+                'thumbnail': r're:^https?://static\.prsa\.pl/images/.*\.jpg$'

             },
         }],
     }, {
             },
         }],
     }, {


@@ -62,7 +65,7 @@ class PolskieRadioIE(InfoExtractor):
         webpage = self._download_webpage(url, playlist_id)
 
         content = self._search_regex(
         webpage = self._download_webpage(url, playlist_id)
 
         content = self._search_regex(

-            r'(?s)<div[^>]+class="audio atarticle"[^>]*>(.+?)<script>',
+            r'(?s)<div[^>]+class="\s*this-article\s*"[^>]*>(.+?)<div[^>]+class="tags"[^>]*>',

             webpage, 'content')
 
         timestamp = unified_timestamp(self._html_search_regex(
             webpage, 'content')
 
         timestamp = unified_timestamp(self._html_search_regex(


@@ -97,3 +100,81 @@ class PolskieRadioIE(InfoExtractor):
         description = strip_or_none(self._og_search_description(webpage))
 
         return self.playlist_result(entries, playlist_id, title, description)
         description = strip_or_none(self._og_search_description(webpage))
 
         return self.playlist_result(entries, playlist_id, title, description)

+
+
+class PolskieRadioCategoryIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?polskieradio\.pl/\d+(?:,[^/]+)?/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://www.polskieradio.pl/7/5102,HISTORIA-ZYWA',
+        'info_dict': {
+            'id': '5102',
+            'title': 'HISTORIA ŻYWA',
+        },
+        'playlist_mincount': 38,
+    }, {
+        'url': 'http://www.polskieradio.pl/7/4807',
+        'info_dict': {
+            'id': '4807',
+            'title': 'Vademecum 1050. rocznicy Chrztu Polski'
+        },
+        'playlist_mincount': 5
+    }, {
+        'url': 'http://www.polskieradio.pl/7/129,Sygnaly-dnia?ref=source',
+        'only_matching': True
+    }, {
+        'url': 'http://www.polskieradio.pl/37,RedakcjaKatolicka/4143,Kierunek-Krakow',
+        'info_dict': {
+            'id': '4143',
+            'title': 'Kierunek Kraków',
+        },
+        'playlist_mincount': 61
+    }, {
+        'url': 'http://www.polskieradio.pl/10,czworka/214,muzyka',
+        'info_dict': {
+            'id': '214',
+            'title': 'Muzyka',
+        },
+        'playlist_mincount': 61
+    }, {
+        'url': 'http://www.polskieradio.pl/7,Jedynka/5102,HISTORIA-ZYWA',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.polskieradio.pl/8,Dwojka/196,Publicystyka',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if PolskieRadioIE.suitable(url) else super(PolskieRadioCategoryIE, cls).suitable(url)
+
+    def _entries(self, url, page, category_id):
+        content = page
+        for page_num in itertools.count(2):
+            for a_entry, entry_id in re.findall(
+                    r'(?s)<article[^>]+>.*?(<a[^>]+href=["\']/\d+/\d+/Artykul/(\d+)[^>]+>).*?</article>',
+                    content):
+                entry = extract_attributes(a_entry)
+                href = entry.get('href')
+                if not href:
+                    continue
+                yield self.url_result(
+                    compat_urlparse.urljoin(url, href), PolskieRadioIE.ie_key(),
+                    entry_id, entry.get('title'))
+            mobj = re.search(
+                r'<div[^>]+class=["\']next["\'][^>]*>\s*<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1',
+                content)
+            if not mobj:
+                break
+            next_url = compat_urlparse.urljoin(url, mobj.group('url'))
+            content = self._download_webpage(
+                next_url, category_id, 'Downloading page %s' % page_num)
+
+    def _real_extract(self, url):
+        category_id = self._match_id(url)
+        webpage = self._download_webpage(url, category_id)
+        title = self._html_search_regex(
+            r'<title>([^<]+) - [^<]+ - [^<]+</title>',
+            webpage, 'title', fatal=False)
+        return self.playlist_result(
+            self._entries(url, webpage, category_id),
+            category_id, title)