import math
import operator
import re
+import urllib.request
from .common import InfoExtractor
-from ..compat import (
- compat_HTTPError,
- compat_str,
- compat_urllib_request,
-)
from .openload import PhantomJSwrapper
+from ..compat import compat_HTTPError, compat_str
from ..utils import (
+ NO_DEFAULT,
+ ExtractorError,
clean_html,
determine_ext,
- ExtractorError,
format_field,
int_or_none,
merge_dicts,
- NO_DEFAULT,
orderedSet,
remove_quotes,
remove_start,
str_to_int,
update_url_query,
- urlencode_postdata,
url_or_none,
+ urlencode_postdata,
)
r'document\.location\.reload\(true\)')):
url_or_request = args[0]
url = (url_or_request.get_full_url()
- if isinstance(url_or_request, compat_urllib_request.Request)
+ if isinstance(url_or_request, urllib.request.Request)
else url_or_request)
phantom = PhantomJSwrapper(self, required_version='2.0')
phantom.get(url, html=webpage)
)
(?P<id>[\da-z]+)
''' % PornHubBaseIE._PORNHUB_HOST_RE
+ _EMBED_REGEX = [r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub(?:premium)?\.(?:com|net|org)/embed/[\da-z]+)']
_TESTS = [{
'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
'md5': 'a6391306d050e4547f62b3f485dd9ba9',
'only_matching': True,
}]
- @staticmethod
- def _extract_urls(webpage):
- return re.findall(
- r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub(?:premium)?\.(?:com|net|org)/embed/[\da-z]+)',
- webpage)
-
def _extract_count(self, pattern, webpage, name):
return str_to_int(self._search_regex(pattern, webpage, '%s count' % name, default=None))
continue
add_format(video_url)
- # field_preference is unnecessary here, but kept for code-similarity with youtube-dl
- self._sort_formats(
- formats, field_preference=('height', 'width', 'fps', 'format_id'))
-
model_profile = self._search_json(
r'var\s+MODEL_PROFILE\s*=', webpage, 'model profile', video_id, fatal=False)
video_uploader = self._html_search_regex(