dbrun
/
youtube-dl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Merge branch 'bandcamp-albums-regex-duplicate-fix' of https://github.com/codesparkle/youtube-dl into codesparkle-bandcamp-albums-regex-duplicate-fix

This commit is contained in:
Sergey M․ 2014-05-20 19:38:28 +07:00
parent f50ee8d1c3 79981f039b
commit d6e4ba287b
1 changed files with 16 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
youtube_dl/extractor/bandcamp.py
View File

@ -19,7 +19,7 @@ class BandcampIE(InfoExtractor):
'md5': 'c557841d5e50261777a6585648adf439', 'md5': 'c557841d5e50261777a6585648adf439',
'info_dict': { 'info_dict': {
"title": "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad", "title": "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad",
"duration": 10, "duration": 9.8485,
}, },
'_skip': 'There is a limit of 200 free downloads / month for the test song' '_skip': 'There is a limit of 200 free downloads / month for the test song'
}] }]
@ -28,36 +28,32 @@ class BandcampIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
title = mobj.group('title') title = mobj.group('title')
webpage = self._download_webpage(url, title) webpage = self._download_webpage(url, title)
# We get the link to the free download page
m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage) m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
if m_download is None: if not m_download:
m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage) m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage)
if m_trackinfo: if m_trackinfo:
json_code = m_trackinfo.group(1) json_code = m_trackinfo.group(1)
data = json.loads(json_code) data = json.loads(json_code)[0]
d = data[0]
duration = int(round(d['duration']))
formats = [] formats = []
for format_id, format_url in d['file'].items(): for format_id, format_url in data['file'].items():
ext, _, abr_str = format_id.partition('-') ext, abr_str = format_id.split('-', maxsplit=1)
formats.append({ formats.append({
'format_id': format_id, 'format_id': format_id,
'url': format_url, 'url': format_url,
'ext': format_id.partition('-')[0], 'ext': ext,
'vcodec': 'none', 'vcodec': 'none',
'acodec': format_id.partition('-')[0], 'acodec': ext,
'abr': int(format_id.partition('-')[2]), 'abr': int(abr_str),
}) })
self._sort_formats(formats) self._sort_formats(formats)
return { return {
'id': compat_str(d['id']), 'id': compat_str(data['id']),
'title': d['title'], 'title': data['title'],
'formats': formats, 'formats': formats,
'duration': duration, 'duration': float(data['duration']),
} }
else: else:
raise ExtractorError('No free songs found') raise ExtractorError('No free songs found')
@ -67,11 +63,9 @@ class BandcampIE(InfoExtractor):
r'var TralbumData = {(.*?)id: (?P<id>\d*?)$', r'var TralbumData = {(.*?)id: (?P<id>\d*?)$',
webpage, re.MULTILINE | re.DOTALL).group('id') webpage, re.MULTILINE | re.DOTALL).group('id')
download_webpage = self._download_webpage(download_link, video_id, download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page')
'Downloading free downloads page') # We get the dictionary of the track from some javascript code
# We get the dictionary of the track from some javascrip code info = re.search(r'items: (.*?),$', download_webpage, re.MULTILINE).group(1)
info = re.search(r'items: (.*?),$',
download_webpage, re.MULTILINE).group(1)
info = json.loads(info)[0] info = json.loads(info)[0]
# We pick mp3-320 for now, until format selection can be easily implemented. # We pick mp3-320 for now, until format selection can be easily implemented.
mp3_info = info['downloads']['mp3-320'] mp3_info = info['downloads']['mp3-320']
@ -100,7 +94,7 @@ class BandcampIE(InfoExtractor):
class BandcampAlbumIE(InfoExtractor): class BandcampAlbumIE(InfoExtractor):
IE_NAME = 'Bandcamp:album' IE_NAME = 'Bandcamp:album'
_VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))?' _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))'
_TEST = { _TEST = {
'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1', 'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
@ -123,7 +117,7 @@ class BandcampAlbumIE(InfoExtractor):
'params': { 'params': {
'playlistend': 2 'playlistend': 2
}, },
'skip': 'Bancamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test' 'skip': 'Bandcamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test'
} }
def _real_extract(self, url): def _real_extract(self, url):