1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 12:38:05 +01:00
youtube-dl/youtube_dl/extractor/playvid.py

89 lines
2.8 KiB
Python
Raw Normal View History

2014-03-10 14:41:19 +01:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_unquote,
compat_urllib_parse_unquote_plus,
)
2014-03-10 14:41:19 +01:00
from ..utils import (
clean_html,
ExtractorError,
2014-03-10 14:41:19 +01:00
)
2014-03-10 20:55:47 +01:00
class PlayvidIE(InfoExtractor):
_VALID_URL = r'https?://www\.playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)'
2014-03-10 14:41:19 +01:00
_TEST = {
'url': 'http://www.playvid.com/watch/RnmBNgtrrJu',
'md5': 'ffa2f6b2119af359f544388d8c01eb6c',
2014-03-10 14:41:19 +01:00
'info_dict': {
'id': 'RnmBNgtrrJu',
2014-03-10 20:55:47 +01:00
'ext': 'mp4',
'title': 'md5:9256d01c6317e3f703848b5906880dc8',
'duration': 82,
2014-03-10 14:41:19 +01:00
'age_limit': 18,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
2014-03-10 14:41:19 +01:00
webpage = self._download_webpage(url, video_id)
m_error = re.search(
r'<div class="block-error">\s*<div class="heading">\s*<div>(?P<msg>.+?)</div>\s*</div>', webpage)
if m_error:
raise ExtractorError(clean_html(m_error.group('msg')), expected=True)
2014-03-10 14:41:19 +01:00
video_title = None
duration = None
video_thumbnail = None
formats = []
# most of the information is stored in the flashvars
2014-03-10 20:55:47 +01:00
flashvars = self._html_search_regex(
r'flashvars="(.+?)"', webpage, 'flashvars')
2014-03-10 14:41:19 +01:00
infos = compat_urllib_parse_unquote(flashvars).split(r'&')
2014-03-10 20:55:47 +01:00
for info in infos:
videovars_match = re.match(r'^video_vars\[(.+?)\]=(.+?)$', info)
if videovars_match:
key = videovars_match.group(1)
val = videovars_match.group(2)
2014-03-10 14:41:19 +01:00
2014-03-10 20:55:47 +01:00
if key == 'title':
video_title = compat_urllib_parse_unquote_plus(val)
2014-03-10 20:55:47 +01:00
if key == 'duration':
try:
duration = int(val)
except ValueError:
pass
if key == 'big_thumb':
video_thumbnail = val
2014-03-10 14:41:19 +01:00
2014-03-10 20:55:47 +01:00
videourl_match = re.match(
r'^video_urls\]\[(?P<resolution>[0-9]+)p', key)
if videourl_match:
height = int(videourl_match.group('resolution'))
formats.append({
'height': height,
'url': val,
})
self._sort_formats(formats)
2014-03-10 14:41:19 +01:00
# Extract title - should be in the flashvars; if not, look elsewhere
if video_title is None:
video_title = self._html_search_regex(
r'<title>(.*?)</title', webpage, 'title')
return {
'id': video_id,
'formats': formats,
'title': video_title,
'thumbnail': video_thumbnail,
'duration': duration,
'description': None,
'age_limit': 18
}