[util] Move compatibility functions out of util

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

diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py
index 2dca5266000db8ed558f149142e3b235e267a910..0bd0eccba8405ada41f948755d6b2f540cc098e1 100644 (file)
--- a/youtube_dl/extractor/crunchyroll.py
+++ b/youtube_dl/extractor/crunchyroll.py
@@ -17,7 +17,6 @@ from ..utils import (
     bytes_to_intlist,
     intlist_to_bytes,
     unified_strdate,
-    clean_html,
     urlencode_postdata,
 )
 from ..aes import (
@@ -109,19 +108,17 @@ class CrunchyrollIE(SubtitlesInfoExtractor):
         decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv))
         return zlib.decompress(decrypted_data)
 
-    def _convert_subtitles_to_srt(self, subtitles):
+    def _convert_subtitles_to_srt(self, sub_root):
         output = ''
-        for i, (start, end, text) in enumerate(re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles), 1):
-            start = start.replace('.', ',')
-            end = end.replace('.', ',')
-            text = clean_html(text)
-            text = text.replace('\\N', '\n')
-            if not text:
-                continue
+
+        for i, event in enumerate(sub_root.findall('./events/event'), 1):
+            start = event.attrib['start'].replace('.', ',')
+            end = event.attrib['end'].replace('.', ',')
+            text = event.attrib['text'].replace('\\N', '\n')
             output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
         return output
 
-    def _convert_subtitles_to_ass(self, subtitles):
+    def _convert_subtitles_to_ass(self, sub_root):
         output = ''
 
         def ass_bool(strvalue):
@@ -130,10 +127,6 @@ class CrunchyrollIE(SubtitlesInfoExtractor):
                 assvalue = '-1'
             return assvalue
 
-        sub_root = xml.etree.ElementTree.fromstring(subtitles)
-        if not sub_root:
-            return output
-
         output = '[Script Info]\n'
         output += 'Title: %s\n' % sub_root.attrib["title"]
         output += 'ScriptType: v4.00+\n'
@@ -270,10 +263,13 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False)
             if not lang_code:
                 continue
+            sub_root = xml.etree.ElementTree.fromstring(subtitle)
+            if not sub_root:
+                subtitles[lang_code] = ''
             if sub_format == 'ass':
-                subtitles[lang_code] = self._convert_subtitles_to_ass(subtitle)
+                subtitles[lang_code] = self._convert_subtitles_to_ass(sub_root)
             else:
-                subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle)
+                subtitles[lang_code] = self._convert_subtitles_to_srt(sub_root)
 
         if self._downloader.params.get('listsubtitles', False):
             self._list_available_subtitles(video_id, subtitles)
@@ -293,34 +289,36 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 
 class CrunchyrollShowPlaylistIE(InfoExtractor):
     IE_NAME = "crunchyroll:playlist"
-    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<show>[\w\-]+))/?$'
-    _TITLE_EXTR = r'<span\s+itemprop="name">\s*(?P<showtitle>[\w\s]+)'
+    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<id>[\w\-]+))/?$'
 
     _TESTS = [{
-        'url' : 'http://www.crunchyroll.com/attack-on-titan',
-        'info_dict' : {
-            'title' : 'Attack on Titan'
+        'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
+        'info_dict': {
+            'id': 'a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
+            'title': 'A Bridge to the Starry Skies - Hoshizora e Kakaru Hashi'
         },
-        'playlist_count' : 15
+        'playlist_count': 13,
     }]
 
-    def _extract_title_entries(self,id,webpage):
-        _EPISODE_ID_EXTR = r'id="showview_videos_media_(?P<vidid>\d+)".*?href="/{0}/(?P<vidurl>[\w\-]+-(?P=vidid))"'.format(id)
-        title = self._html_search_regex(self._TITLE_EXTR,webpage,"title",flags=re.UNICODE|re.MULTILINE)
-        episode_urls = [self.url_result('http://www.crunchyroll.com/{0}/{1}'.format(id, showmatch[1])) for
-                    showmatch in re.findall(_EPISODE_ID_EXTR, webpage,re.UNICODE|re.MULTILINE|re.DOTALL)]
-        episode_urls.reverse()
-        return title, episode_urls
-
-
     def _real_extract(self, url):
-        url_match = re.match(self._VALID_URL,url)
-        show_id = url_match.group('show')
-        webpage = self._download_webpage(url,show_id)
-        (title,entries) = self._extract_title_entries(show_id,webpage)
+        show_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, show_id)
+        title = self._html_search_regex(
+            r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
+            webpage, 'title')
+        episode_paths = re.findall(
+            r'(?s)<li id="showview_videos_media_[0-9]+"[^>]+>.*?<a href="([^"]+)"',
+            webpage)
+        entries = [
+            self.url_result('http://www.crunchyroll.com' + ep, 'Crunchyroll')
+            for ep in episode_paths
+        ]
+        entries.reverse()
+
         return {
-            '_type' : 'playlist',
-            'id' : show_id,
-            'title' : title,
-            'entries' : entries
-        }
\ No newline at end of file
+            '_type': 'playlist',
+            'id': show_id,
+            'title': title,
+            'entries': entries,
+        }