diff options
| author | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2013-12-10 21:03:53 +0100 |
|---|---|---|
| committer | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2013-12-10 21:03:53 +0100 |
| commit | 182583623583c8e71af9b4e24acf8c409fcff197 (patch) | |
| tree | c049216db457bd6b4592862eab000afb66a4088e /youtube_dl/extractor/appletrailers.py | |
| parent | a0088bdf9342408a1fc5033a0f4599bae3b9aa0b (diff) | |
Use `_download_xml` in more extractors
Diffstat (limited to 'youtube_dl/extractor/appletrailers.py')
| -rw-r--r-- | youtube_dl/extractor/appletrailers.py | 23 |
1 files changed, 11 insertions, 12 deletions
diff --git a/youtube_dl/extractor/appletrailers.py b/youtube_dl/extractor/appletrailers.py index a527f10de..ef5644aa5 100644 --- a/youtube_dl/extractor/appletrailers.py +++ b/youtube_dl/extractor/appletrailers.py @@ -1,5 +1,4 @@ import re -import xml.etree.ElementTree import json from .common import InfoExtractor @@ -65,18 +64,18 @@ class AppleTrailersIE(InfoExtractor): uploader_id = mobj.group('company') playlist_url = compat_urlparse.urljoin(url, u'includes/playlists/itunes.inc') - playlist_snippet = self._download_webpage(playlist_url, movie) - playlist_cleaned = re.sub(r'(?s)<script[^<]*?>.*?</script>', u'', playlist_snippet) - playlist_cleaned = re.sub(r'<img ([^<]*?)>', r'<img \1/>', playlist_cleaned) - # The ' in the onClick attributes are not escaped, it couldn't be parsed - # with xml.etree.ElementTree.fromstring - # like: http://trailers.apple.com/trailers/wb/gravity/ - def _clean_json(m): - return u'iTunes.playURL(%s);' % m.group(1).replace('\'', ''') - playlist_cleaned = re.sub(self._JSON_RE, _clean_json, playlist_cleaned) - playlist_html = u'<html>' + playlist_cleaned + u'</html>' + def fix_html(s): + s = re.sub(r'(?s)<script[^<]*?>.*?</script>', u'', s) + s = re.sub(r'<img ([^<]*?)>', r'<img \1/>', s) + # The ' in the onClick attributes are not escaped, it couldn't be parsed + # like: http://trailers.apple.com/trailers/wb/gravity/ + def _clean_json(m): + return u'iTunes.playURL(%s);' % m.group(1).replace('\'', ''') + s = re.sub(self._JSON_RE, _clean_json, s) + s = u'<html>' + s + u'</html>' + return s + doc = self._download_xml(playlist_url, movie, transform_source=fix_html) - doc = xml.etree.ElementTree.fromstring(playlist_html) playlist = [] for li in doc.findall('./div/ul/li'): on_click = li.find('.//a').attrib['onClick'] |