Merge branch 'polskie-radio-programme' of https://github.com/JakubAdamWieczorek/youtu...

[youtube-dl] / youtube_dl / extractor / polskieradio.py

diff --git a/youtube_dl/extractor/polskieradio.py b/youtube_dl/extractor/polskieradio.py
index f5adff08ffd91bc01bffd57be3814e75415d553f..c51d3d9be0fd45398d903e39b99e817d7f61ccdc 100644 (file)
--- a/youtube_dl/extractor/polskieradio.py
+++ b/youtube_dl/extractor/polskieradio.py
@@ -7,6 +7,7 @@ from .common import InfoExtractor
 from ..compat import (
     compat_str,
     compat_urllib_parse_unquote,
+    compat_urlparse
 )
 from ..utils import (
     int_or_none,
@@ -15,6 +16,84 @@ from ..utils import (
 )
 
 
+class PolskieRadioProgrammeIE(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': 34,
+    }, {
+        '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/7,Jedynka/5102,HISTORIA-ZYWA',
+        'only_matching': True
+    }]
+
+    def _get_entries_from_page_content(self, base_url, content):
+        entries = []
+
+        articles = re.findall(
+            r'<article class="ID-(\d+) article">\s+<a href="([^"]+)"( data-layer="[^"]*")? class="[^"]*" title="([^"]+)">',
+            content)
+        for article_id, article_url, _, article_title in articles:
+            resolved_article_url = compat_urlparse.urljoin(base_url, article_url)
+            entries.append(self.url_result(
+                resolved_article_url,
+                ie='PolskieRadio',
+                video_id=article_id,
+                video_title=article_title))
+
+        return entries
+
+    @classmethod
+    def suitable(cls, url):
+        return False if PolskieRadioIE.suitable(url) else super(PolskieRadioProgrammeIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        programme_id = self._match_id(url)
+        webpage = self._download_webpage(url, programme_id)
+
+        title = self._html_search_regex(
+            r'<a href="[^"]+" id=".*_linkCategory" title="[^"]+">(.+?)</a>',
+            webpage, 'title', fatal=False)
+        description = None
+
+        entries = self._get_entries_from_page_content(url, webpage)
+
+        pages = re.findall(r'<a( href="([^"]+/Strona/)\d+")? id="[^"]+" title="strona&#32;(\d+)"', webpage)
+        page_count = max(int(page_number) for _, _, page_number in pages) if pages else 1
+
+        if page_count > 1:
+            page_url_root = next(url for _, url, _ in pages if len(url) > 0)
+            for page_number in range(2, page_count + 1):
+                page_url = page_url_root + str(page_number)
+                resolved_page_url = compat_urlparse.urljoin(url, page_url)
+                page_content = self._download_webpage(
+                    resolved_page_url, programme_id,
+                    note="Downloading page number %d" % page_number)
+                entries.extend(self._get_entries_from_page_content(url, page_content))
+
+        return self.playlist_result(entries, programme_id, title, description)
+
+
 class PolskieRadioIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?polskieradio\.pl/\d+/\d+/Artykul/(?P<id>[0-9]+)'
     _TESTS = [{
@@ -33,6 +112,7 @@ class PolskieRadioIE(InfoExtractor):
                 'timestamp': 1456594200,
                 'upload_date': '20160227',
                 'duration': 2364,
+                'thumbnail': 're:^https?://static\.prsa\.pl/images/.*\.jpg$'
             },
         }],
     }, {
@@ -49,6 +129,10 @@ class PolskieRadioIE(InfoExtractor):
     }, {
         'url': 'http://www.polskieradio.pl/7/5102/Artykul/1587943',
         'only_matching': True,
+    }, {
+        # with mp4 video
+        'url': 'http://www.polskieradio.pl/9/299/Artykul/1634903,Brexit-Leszek-Miller-swiat-sie-nie-zawali-Europa-bedzie-trwac-dalej',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -64,6 +148,8 @@ class PolskieRadioIE(InfoExtractor):
             r'(?s)<span[^>]+id="datetime2"[^>]*>(.+?)</span>',
             webpage, 'timestamp', fatal=False))
 
+        thumbnail_url = self._og_search_thumbnail(webpage)
+
         entries = []
 
         media_urls = set()
@@ -83,6 +169,7 @@ class PolskieRadioIE(InfoExtractor):
                 'duration': int_or_none(media.get('length')),
                 'vcodec': 'none' if media.get('provider') == 'audio' else None,
                 'timestamp': timestamp,
+                'thumbnail': thumbnail_url
             })
 
         title = self._og_search_title(webpage).strip()