diff --git a/youtube_dl/extractor/appletrailers.py b/youtube_dl/extractor/appletrailers.py
index 922cede056..fc5d6825e3 100644
--- a/youtube_dl/extractor/appletrailers.py
+++ b/youtube_dl/extractor/appletrailers.py
@@ -16,9 +16,10 @@ class AppleTrailersIE(InfoExtractor):
"url": "http://trailers.apple.com/trailers/wb/manofsteel/",
"playlist": [
{
- "file": "manofsteel-trailer4.mov",
"md5": "d97a8e575432dbcb81b7c3acb741f8a8",
"info_dict": {
+ "id": "manofsteel-trailer4",
+ "ext": "mov",
"duration": 111,
"title": "Trailer 4",
"upload_date": "20130523",
@@ -26,9 +27,10 @@ class AppleTrailersIE(InfoExtractor):
},
},
{
- "file": "manofsteel-trailer3.mov",
"md5": "b8017b7131b721fb4e8d6f49e1df908c",
"info_dict": {
+ "id": "manofsteel-trailer3",
+ "ext": "mov",
"duration": 182,
"title": "Trailer 3",
"upload_date": "20130417",
@@ -36,9 +38,10 @@ class AppleTrailersIE(InfoExtractor):
},
},
{
- "file": "manofsteel-trailer.mov",
"md5": "d0f1e1150989b9924679b441f3404d48",
"info_dict": {
+ "id": "manofsteel-trailer",
+ "ext": "mov",
"duration": 148,
"title": "Trailer",
"upload_date": "20121212",
@@ -46,15 +49,16 @@ class AppleTrailersIE(InfoExtractor):
},
},
{
- "file": "manofsteel-teaser.mov",
"md5": "5fe08795b943eb2e757fa95cb6def1cb",
"info_dict": {
+ "id": "manofsteel-teaser",
+ "ext": "mov",
"duration": 93,
"title": "Teaser",
"upload_date": "20120721",
"uploader_id": "wb",
},
- }
+ },
]
}
@@ -65,16 +69,16 @@ def _real_extract(self, url):
movie = mobj.group('movie')
uploader_id = mobj.group('company')
- playlist_url = compat_urlparse.urljoin(url, u'includes/playlists/itunes.inc')
+ playlist_url = compat_urlparse.urljoin(url, 'includes/playlists/itunes.inc')
def fix_html(s):
- s = re.sub(r'(?s)', u'', s)
+ s = re.sub(r'(?s)', '', s)
s = re.sub(r'
', r'
', 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('\'', ''')
+ return 'iTunes.playURL(%s);' % m.group(1).replace('\'', ''')
s = re.sub(self._JSON_RE, _clean_json, s)
- s = u'' + s + u''
+ s = '' + s + u''
return s
doc = self._download_xml(playlist_url, movie, transform_source=fix_html)
@@ -82,7 +86,7 @@ def _clean_json(m):
for li in doc.findall('./div/ul/li'):
on_click = li.find('.//a').attrib['onClick']
trailer_info_json = self._search_regex(self._JSON_RE,
- on_click, u'trailer info')
+ on_click, 'trailer info')
trailer_info = json.loads(trailer_info_json)
title = trailer_info['title']
video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower()
@@ -98,8 +102,7 @@ def _clean_json(m):
first_url = trailer_info['url']
trailer_id = first_url.split('/')[-1].rpartition('_')[0].lower()
settings_json_url = compat_urlparse.urljoin(url, 'includes/settings/%s.json' % trailer_id)
- settings_json = self._download_webpage(settings_json_url, trailer_id, u'Downloading settings json')
- settings = json.loads(settings_json)
+ settings = self._download_json(settings_json_url, trailer_id, 'Downloading settings json')
formats = []
for format in settings['metadata']['sizes']:
@@ -107,7 +110,6 @@ def _clean_json(m):
format_url = re.sub(r'_(\d*p.mov)', r'_h\1', format['src'])
formats.append({
'url': format_url,
- 'ext': determine_ext(format_url),
'format': format['type'],
'width': format['width'],
'height': int(format['height']),