[ccc] Extract duration

This commit is contained in:
Sergey M․ 2016-01-01 15:41:52 +06:00
parent 8499d21158
commit 82597f0ec0

View File

@ -5,6 +5,7 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
parse_duration,
qualities, qualities,
unified_strdate, unified_strdate,
) )
@ -25,6 +26,7 @@ class CCCIE(InfoExtractor):
'thumbnail': 're:^https?://.*\.jpg$', 'thumbnail': 're:^https?://.*\.jpg$',
'view_count': int, 'view_count': int,
'upload_date': '20131228', 'upload_date': '20131228',
'duration': 3660,
} }
}, { }, {
'url': 'https://media.ccc.de/v/32c3-7368-shopshifting#download', 'url': 'https://media.ccc.de/v/32c3-7368-shopshifting#download',
@ -51,6 +53,9 @@ def _real_extract(self, url):
view_count = int_or_none(self._html_search_regex( view_count = int_or_none(self._html_search_regex(
r"(?s)<span class='[^']*fa-eye'></span>(.*?)</li>", r"(?s)<span class='[^']*fa-eye'></span>(.*?)</li>",
webpage, 'view count', fatal=False)) webpage, 'view count', fatal=False))
duration = parse_duration(self._html_search_regex(
r'(?s)<span[^>]+class=(["\']).*?fa-clock-o.*?\1[^>]*></span>(?P<duration>.+?)</li',
webpage, 'duration', fatal=False, group='duration'))
matches = re.finditer(r'''(?xs) matches = re.finditer(r'''(?xs)
<(?:span|div)\s+class='label\s+filetype'>(?P<format>.*?)</(?:span|div)>\s* <(?:span|div)\s+class='label\s+filetype'>(?P<format>.*?)</(?:span|div)>\s*
@ -98,5 +103,6 @@ def _real_extract(self, url):
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'view_count': view_count, 'view_count': view_count,
'upload_date': upload_date, 'upload_date': upload_date,
'duration': duration,
'formats': formats, 'formats': formats,
} }