MarcoBuster/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-26 13:15:51 +01:00
Code Issues Projects Releases Wiki Activity

[spankwire] Simplify and properly format

Browse Source
This commit is contained in:
Sergey M․ 2015-08-23 22:32:20 +06:00
parent 59e6acc757
commit 551c7837ac
1 changed files with 45 additions and 60 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
youtube_dl/extractor/spankwire.py
View File

@ -18,6 +18,7 @@
class SpankwireIE(InfoExtractor): class SpankwireIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<videoid>[0-9]+)/?)' _VALID_URL = r'https?://(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<videoid>[0-9]+)/?)'
_TESTS = [{ _TESTS = [{
# download URL pattern: */<height>P_<tbr>K_<video_id>.mp4
'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/', 'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
'md5': '8bbfde12b101204b39e4b9fe7eb67095', 'md5': '8bbfde12b101204b39e4b9fe7eb67095',
'info_dict': { 'info_dict': {
@ -30,8 +31,8 @@ class SpankwireIE(InfoExtractor):
'upload_date': '20070507', 'upload_date': '20070507',
'age_limit': 18, 'age_limit': 18,
} }
}, }, {
{ # download URL pattern: */mp4_<format_id>_<video_id>.mp4
'url': 'http://www.spankwire.com/Titcums-Compiloation-I/video1921551/', 'url': 'http://www.spankwire.com/Titcums-Compiloation-I/video1921551/',
'md5': '09b3c20833308b736ae8902db2f8d7e6', 'md5': '09b3c20833308b736ae8902db2f8d7e6',
'info_dict': { 'info_dict': {
@ -43,7 +44,7 @@ class SpankwireIE(InfoExtractor):
'uploader_id': '3056053', 'uploader_id': '3056053',
'upload_date': '20150822', 'upload_date': '20150822',
'age_limit': 18, 'age_limit': 18,
} },
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -81,9 +82,10 @@ def _real_extract(self, url):
r'<span\s+id="spCommentCount"[^>]*>([\d,\.]+)</span>', r'<span\s+id="spCommentCount"[^>]*>([\d,\.]+)</span>',
webpage, 'comment count', fatal=False)) webpage, 'comment count', fatal=False))
video_urls = list(map( videos = re.findall(
compat_urllib_parse_unquote, r'playerData\.cdnPath([0-9]{3,})\s*=\s*(?:encodeURIComponent\()?["\']([^"\']+)["\']', webpage)
re.findall(r'playerData\.cdnPath[0-9]{3,}\s*=\s*(?:encodeURIComponent\()?["\']([^"\']+)["\']', webpage))) heights = [int(video[0]) for video in videos]
video_urls = list(map(compat_urllib_parse_unquote, [video[1] for video in videos]))
if webpage.find('flashvars\.encrypted = "true"') != -1: if webpage.find('flashvars\.encrypted = "true"') != -1:
password = self._search_regex( password = self._search_regex(
r'flashvars\.video_title = "([^"]+)', r'flashvars\.video_title = "([^"]+)',
@ -93,39 +95,22 @@ def _real_extract(self, url):
video_urls)) video_urls))
formats = [] formats = []
for video_url in video_urls: for height, video_url in zip(heights, video_urls):
path = compat_urllib_parse_urlparse(video_url).path path = compat_urllib_parse_urlparse(video_url).path
format = path.split('/')[4].split('_')[:2] _, quality = path.split('/')[4].split('_')[:2]
if format[0] == 'mp4': f = {
format_id, quality = format
format = "-".join(format)
if quality == 'normal':
height = 180
elif quality == 'high':
height = 240
elif quality == 'ultra':
height = 480
elif quality == '720p':
height = 720
formats.append({
'url': video_url, 'url': video_url,
'format': format,
'height': height, 'height': height,
'format_id': format, }
tbr = self._search_regex(r'^(\d+)[Kk]$', quality, 'tbr', default=None)
if tbr:
f.update({
'tbr': int(tbr),
'format_id': '%dp' % height,
}) })
else: else:
resolution, bitrate_str = format f['format_id'] = quality
format = "-".join(format) formats.append(f)
height = int(resolution.rstrip('Pp'))
tbr = int(bitrate_str.rstrip('Kk'))
formats.append({
'url': video_url,
'resolution': resolution,
'format': format,
'tbr': tbr,
'height': height,
'format_id': format,
})
self._sort_formats(formats) self._sort_formats(formats)
age_limit = self._rta_search(webpage) age_limit = self._rta_search(webpage)