You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
yt-dlp/yt_dlp/extractor/playvid.py

91 lines
3.1 KiB
Python

11 years ago
import re
import urllib.parse
11 years ago
from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote
from ..utils import ExtractorError, clean_html
11 years ago
class PlayvidIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)'
_TESTS = [{
'url': 'http://www.playvid.com/watch/RnmBNgtrrJu',
'md5': 'ffa2f6b2119af359f544388d8c01eb6c',
11 years ago
'info_dict': {
'id': 'RnmBNgtrrJu',
'ext': 'mp4',
'title': 'md5:9256d01c6317e3f703848b5906880dc8',
'duration': 82,
11 years ago
'age_limit': 18,
},
'skip': 'Video removed due to ToS',
}, {
'url': 'http://www.playvid.com/watch/hwb0GpNkzgH',
'md5': '39d49df503ad7b8f23a4432cbf046477',
'info_dict': {
'id': 'hwb0GpNkzgH',
'ext': 'mp4',
'title': 'Ellen Euro Cutie Blond Takes a Sexy Survey Get Facial in The Park',
'age_limit': 18,
'thumbnail': r're:^https?://.*\.jpg$',
},
}]
11 years ago
def _real_extract(self, url):
video_id = self._match_id(url)
11 years ago
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)
11 years ago
video_title = None
duration = None
video_thumbnail = None
formats = []
# most of the information is stored in the flashvars
flashvars = self._html_search_regex(
r'flashvars="(.+?)"', webpage, 'flashvars')
11 years ago
infos = compat_urllib_parse_unquote(flashvars).split(r'&')
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)
11 years ago
if key == 'title':
video_title = urllib.parse.unquote_plus(val)
if key == 'duration':
try:
duration = int(val)
except ValueError:
pass
if key == 'big_thumb':
video_thumbnail = val
11 years ago
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,
})
11 years ago
# Extract title - should be in the flashvars; if not, look elsewhere
if video_title is None:
video_title = self._html_extract_title(webpage)
11 years ago
return {
'id': video_id,
'formats': formats,
'title': video_title,
'thumbnail': video_thumbnail,
'duration': duration,
'description': None,
'age_limit': 18
}