mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-12-24 00:46:51 +00:00
Merge branch 'peugeot-vporn'
This commit is contained in:
commit
6a400a6339
@ -211,6 +211,9 @@ class TestUtil(unittest.TestCase):
|
|||||||
self.assertEqual(parse_duration('00:01:01'), 61)
|
self.assertEqual(parse_duration('00:01:01'), 61)
|
||||||
self.assertEqual(parse_duration('x:y'), None)
|
self.assertEqual(parse_duration('x:y'), None)
|
||||||
self.assertEqual(parse_duration('3h11m53s'), 11513)
|
self.assertEqual(parse_duration('3h11m53s'), 11513)
|
||||||
|
self.assertEqual(parse_duration('3h 11m 53s'), 11513)
|
||||||
|
self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
|
||||||
|
self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
|
||||||
self.assertEqual(parse_duration('62m45s'), 3765)
|
self.assertEqual(parse_duration('62m45s'), 3765)
|
||||||
self.assertEqual(parse_duration('6m59s'), 419)
|
self.assertEqual(parse_duration('6m59s'), 419)
|
||||||
self.assertEqual(parse_duration('49s'), 49)
|
self.assertEqual(parse_duration('49s'), 49)
|
||||||
|
@ -393,6 +393,7 @@ from .vine import (
|
|||||||
from .viki import VikiIE
|
from .viki import VikiIE
|
||||||
from .vk import VKIE
|
from .vk import VKIE
|
||||||
from .vodlocker import VodlockerIE
|
from .vodlocker import VodlockerIE
|
||||||
|
from .vporn import VpornIE
|
||||||
from .vube import VubeIE
|
from .vube import VubeIE
|
||||||
from .vuclip import VuClipIE
|
from .vuclip import VuClipIE
|
||||||
from .vulture import VultureIE
|
from .vulture import VultureIE
|
||||||
|
99
youtube_dl/extractor/vporn.py
Normal file
99
youtube_dl/extractor/vporn.py
Normal file
@ -0,0 +1,99 @@
|
|||||||
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
|
import re
|
||||||
|
|
||||||
|
from .common import InfoExtractor
|
||||||
|
from ..utils import (
|
||||||
|
parse_duration,
|
||||||
|
str_to_int,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
class VpornIE(InfoExtractor):
|
||||||
|
_VALID_URL = r'https?://(?:www\.)?vporn\.com/[^/]+/(?P<display_id>[^/]+)/(?P<id>\d+)'
|
||||||
|
_TEST = {
|
||||||
|
'url': 'http://www.vporn.com/masturbation/violet-on-her-th-birthday/497944/',
|
||||||
|
'md5': 'facf37c1b86546fa0208058546842c55',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '497944',
|
||||||
|
'display_id': 'violet-on-her-th-birthday',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': 'Violet on her 19th birthday',
|
||||||
|
'description': 'Violet dances in front of the camera which is sure to get you horny.',
|
||||||
|
'thumbnail': 're:^https?://.*\.jpg$',
|
||||||
|
'uploader': 'kileyGrope',
|
||||||
|
'categories': ['Masturbation', 'Teen'],
|
||||||
|
'duration': 393,
|
||||||
|
'age_limit': 18,
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
mobj = re.match(self._VALID_URL, url)
|
||||||
|
video_id = mobj.group('id')
|
||||||
|
display_id = mobj.group('display_id')
|
||||||
|
|
||||||
|
webpage = self._download_webpage(url, display_id)
|
||||||
|
|
||||||
|
title = self._html_search_regex(
|
||||||
|
r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip()
|
||||||
|
description = self._html_search_regex(
|
||||||
|
r'<div class="description_txt">(.*?)</div>', webpage, 'description', fatal=False)
|
||||||
|
thumbnail = self._html_search_regex(
|
||||||
|
r'flashvars\.imageUrl\s*=\s*"([^"]+)"', webpage, 'description', fatal=False, default=None)
|
||||||
|
if thumbnail:
|
||||||
|
thumbnail = 'http://www.vporn.com' + thumbnail
|
||||||
|
|
||||||
|
uploader = self._html_search_regex(
|
||||||
|
r'(?s)UPLOADED BY.*?<a href="/user/[^"]+">([^<]+)</a>',
|
||||||
|
webpage, 'uploader', fatal=False)
|
||||||
|
|
||||||
|
categories = re.findall(r'<a href="/cat/[^"]+">([^<]+)</a>', webpage)
|
||||||
|
|
||||||
|
duration = parse_duration(self._search_regex(
|
||||||
|
r'duration (\d+ min \d+ sec)', webpage, 'duration', fatal=False))
|
||||||
|
|
||||||
|
view_count = str_to_int(self._html_search_regex(
|
||||||
|
r'<span>([\d,\.]+) VIEWS</span>', webpage, 'view count', fatal=False))
|
||||||
|
like_count = str_to_int(self._html_search_regex(
|
||||||
|
r'<span id="like" class="n">([\d,\.]+)</span>', webpage, 'like count', fatal=False))
|
||||||
|
dislike_count = str_to_int(self._html_search_regex(
|
||||||
|
r'<span id="dislike" class="n">([\d,\.]+)</span>', webpage, 'dislike count', fatal=False))
|
||||||
|
comment_count = str_to_int(self._html_search_regex(
|
||||||
|
r'<h4>Comments \(<b>([\d,\.]+)</b>\)</h4>', webpage, 'comment count', fatal=False))
|
||||||
|
|
||||||
|
formats = []
|
||||||
|
|
||||||
|
for video in re.findall(r'flashvars\.videoUrl([^=]+?)\s*=\s*"([^"]+)"', webpage):
|
||||||
|
video_url = video[1]
|
||||||
|
fmt = {
|
||||||
|
'url': video_url,
|
||||||
|
'format_id': video[0],
|
||||||
|
}
|
||||||
|
m = re.search(r'_(?P<width>\d+)x(?P<height>\d+)_(?P<vbr>\d+)k\.mp4$', video_url)
|
||||||
|
if m:
|
||||||
|
fmt.update({
|
||||||
|
'width': int(m.group('width')),
|
||||||
|
'height': int(m.group('height')),
|
||||||
|
'vbr': int(m.group('vbr')),
|
||||||
|
})
|
||||||
|
formats.append(fmt)
|
||||||
|
|
||||||
|
self._sort_formats(formats)
|
||||||
|
|
||||||
|
return {
|
||||||
|
'id': video_id,
|
||||||
|
'display_id': display_id,
|
||||||
|
'title': title,
|
||||||
|
'description': description,
|
||||||
|
'thumbnail': thumbnail,
|
||||||
|
'uploader': uploader,
|
||||||
|
'categories': categories,
|
||||||
|
'duration': duration,
|
||||||
|
'view_count': view_count,
|
||||||
|
'like_count': like_count,
|
||||||
|
'dislike_count': dislike_count,
|
||||||
|
'comment_count': comment_count,
|
||||||
|
'age_limit': 18,
|
||||||
|
'formats': formats,
|
||||||
|
}
|
@ -1332,8 +1332,10 @@ def parse_duration(s):
|
|||||||
if s is None:
|
if s is None:
|
||||||
return None
|
return None
|
||||||
|
|
||||||
|
s = s.strip()
|
||||||
|
|
||||||
m = re.match(
|
m = re.match(
|
||||||
r'(?:(?:(?P<hours>[0-9]+)[:h])?(?P<mins>[0-9]+)[:m])?(?P<secs>[0-9]+)s?(?::[0-9]+)?(?P<ms>\.[0-9]+)?$', s)
|
r'(?:(?:(?P<hours>[0-9]+)\s*(?:[:h]|hours?)\s*)?(?P<mins>[0-9]+)\s*(?:[:m]|mins?|minutes?)\s*)?(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*(?:s|secs?|seconds?)?$', s)
|
||||||
if not m:
|
if not m:
|
||||||
return None
|
return None
|
||||||
res = int(m.group('secs'))
|
res = int(m.group('secs'))
|
||||||
|
Loading…
Reference in New Issue
Block a user