youtube-dl

commit 1115271ac61b89cc4ac1ca922eff8a4bed0fbf57
parent d21d0ba6c14e8a6696130090641da4e2028e1bb3
Author: Sergey M․ <dstftw@gmail.com>
Date:   Sat,  9 Dec 2017 00:46:28 +0700

[raiplay:playlist] Fix issues and improve (closes #14563)

Diffstat:
M
youtube_dl/extractor/extractors.py
 | 
2
+-
M
youtube_dl/extractor/rai.py
 | 
62
++++++++++++++++++++++++++++++++++++--------------------------

2 files changed, 37 insertions(+), 27 deletions(-)
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
@@ -856,8 +856,8 @@ from .radiofrance import RadioFranceIE
 from .rai import (
     RaiPlayIE,
     RaiPlayLiveIE,
+    RaiPlayPlaylistIE,
     RaiIE,
-    RaiPlaylistIE,
 )
 from .rbmaradio import RBMARadioIE
 from .rds import RDSIE
diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py
@@ -17,6 +17,7 @@ from ..utils import (
     parse_duration,
     strip_or_none,
     try_get,
+    unescapeHTML,
     unified_strdate,
     unified_timestamp,
     update_url_query,
@@ -249,6 +250,41 @@ class RaiPlayLiveIE(RaiBaseIE):
         }
 
 
+class RaiPlayPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'http://www.raiplay.it/programmi/nondirloalmiocapo/',
+        'info_dict': {
+            'id': 'nondirloalmiocapo',
+            'title': 'Non dirlo al mio capo',
+            'description': 'md5:9f3d603b2947c1c7abb098f3b14fac86',
+        },
+        'playlist_mincount': 12,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        title = self._html_search_meta(
+            ('programma', 'nomeProgramma'), webpage, 'title')
+        description = unescapeHTML(self._html_search_meta(
+            ('description', 'og:description'), webpage, 'description'))
+        print(description)
+
+        entries = []
+        for mobj in re.finditer(
+                r'<a\b[^>]+\bhref=(["\'])(?P<path>/raiplay/video/.+?)\1',
+                webpage):
+            video_url = urljoin(url, mobj.group('path'))
+            entries.append(self.url_result(
+                video_url, ie=RaiPlayIE.ie_key(),
+                video_id=RaiPlayIE._match_id(video_url)))
+
+        return self.playlist_result(entries, playlist_id, title, description)
+
+
 class RaiIE(RaiBaseIE):
     _VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/dl/.+?-(?P<id>%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE
     _TESTS = [{
@@ -455,29 +491,3 @@ class RaiIE(RaiBaseIE):
         info.update(relinker_info)
 
         return info
-
-
-class RaiPlaylistIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/]+)'
-    _TESTS = [{
-        'url': 'http://www.raiplay.it/programmi/nondirloalmiocapo/',
-        'info_dict': {
-            'id': 'nondirloalmiocapo',
-            'title': 'Non dirlo al mio capo',
-        },
-        'playlist_mincount': 12,
-    }]
-
-    def _real_extract(self, url):
-        playlist_id = self._match_id(url)
-        webpage = self._download_webpage(url, playlist_id)
-        title = self._html_search_meta('programma', webpage, default=None)
-        video_urls = re.findall(' href="(/raiplay/video.+)"', webpage)
-        video_urls = [urljoin(url, video_url) for video_url in video_urls]
-        entries = [
-            self.url_result(
-                video_url,
-                RaiPlayIE.ie_key())
-            for video_url in video_urls if RaiPlayIE.suitable(video_url)
-        ]
-        return self.playlist_result(entries, playlist_id, title)