yt-dlp/yt_dlp/extractor/eroprofile.py

132 lines
4.5 KiB
Python
Raw Normal View History

2014-12-26 17:15:34 +01:00
from __future__ import unicode_literals
2015-03-26 22:24:15 +01:00
import re
2014-12-26 17:15:34 +01:00
from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlencode
from ..utils import (
ExtractorError,
merge_dicts,
)
2014-12-26 17:15:34 +01:00
2014-12-26 18:32:41 +01:00
2014-12-26 17:15:34 +01:00
class EroProfileIE(InfoExtractor):
2014-12-26 18:32:41 +01:00
_VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/view/(?P<id>[^/]+)'
2015-03-26 22:24:15 +01:00
_LOGIN_URL = 'http://www.eroprofile.com/auth/auth.php?'
_NETRC_MACHINE = 'eroprofile'
_TESTS = [{
2014-12-26 17:15:34 +01:00
'url': 'http://www.eroprofile.com/m/videos/view/sexy-babe-softcore',
'md5': 'c26f351332edf23e1ea28ce9ec9de32f',
'info_dict': {
'id': '3733775',
2014-12-26 18:32:41 +01:00
'display_id': 'sexy-babe-softcore',
2014-12-26 17:15:34 +01:00
'ext': 'm4v',
2014-12-26 18:32:41 +01:00
'title': 'sexy babe softcore',
'thumbnail': r're:https?://.*\.jpg',
2014-12-26 17:15:34 +01:00
'age_limit': 18,
},
'skip': 'Video not found',
2015-03-26 22:24:15 +01:00
}, {
'url': 'http://www.eroprofile.com/m/videos/view/Try-It-On-Pee_cut_2-wmv-4shared-com-file-sharing-download-movie-file',
'md5': '1baa9602ede46ce904c431f5418d8916',
'info_dict': {
'id': '1133519',
'ext': 'm4v',
'title': 'Try It On Pee_cut_2.wmv - 4shared.com - file sharing - download movie file',
'thumbnail': r're:https?://.*\.jpg',
2015-03-26 22:24:15 +01:00
'age_limit': 18,
},
'skip': 'Requires login',
}]
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
query = compat_urllib_parse_urlencode({
2015-03-26 22:24:15 +01:00
'username': username,
'password': password,
'url': 'http://www.eroprofile.com/',
})
login_url = self._LOGIN_URL + query
login_page = self._download_webpage(login_url, None, False)
m = re.search(r'Your username or password was incorrect\.', login_page)
if m:
raise ExtractorError(
'Wrong username and/or password.', expected=True)
self.report_login()
redirect_url = self._search_regex(
r'<script[^>]+?src="([^"]+)"', login_page, 'login redirect url')
self._download_webpage(redirect_url, None, False)
def _real_initialize(self):
self._login()
2014-12-26 17:15:34 +01:00
def _real_extract(self, url):
2014-12-26 18:32:41 +01:00
display_id = self._match_id(url)
2014-12-26 17:15:34 +01:00
2014-12-26 18:32:41 +01:00
webpage = self._download_webpage(url, display_id)
2014-12-26 17:15:34 +01:00
2015-03-26 22:24:15 +01:00
m = re.search(r'You must be logged in to view this video\.', webpage)
if m:
2015-08-26 17:25:37 +02:00
self.raise_login_required('This video requires login')
2015-03-26 22:24:15 +01:00
2014-12-26 18:32:41 +01:00
video_id = self._search_regex(
[r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'],
webpage, 'video id', default=None)
2014-12-26 17:15:34 +01:00
title = self._html_search_regex(
(r'Title:</th><td>([^<]+)</td>', r'<h1[^>]*>(.+?)</h1>'),
webpage, 'title')
info = self._parse_html5_media_entries(url, webpage, video_id)[0]
2014-12-26 17:15:34 +01:00
return merge_dicts(info, {
2014-12-26 17:15:34 +01:00
'id': video_id,
2014-12-26 18:32:41 +01:00
'display_id': display_id,
2014-12-26 17:15:34 +01:00
'title': title,
'age_limit': 18,
})
class EroProfileAlbumIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/album/(?P<id>[^/]+)'
IE_NAME = 'EroProfile:album'
_TESTS = [{
'url': 'https://www.eroprofile.com/m/videos/album/BBW-2-893',
'info_dict': {
'id': 'BBW-2-893',
'title': 'BBW 2'
},
'playlist_mincount': 486,
},
]
def _extract_from_page(self, page):
for url in re.findall(r'href=".*?(/m/videos/view/[^"]+)"', page):
yield self.url_result(f'https://www.eroprofile.com{url}', EroProfileIE.ie_key())
def _entries(self, playlist_id, first_page):
yield from self._extract_from_page(first_page)
page_urls = re.findall(rf'href=".*?(/m/videos/album/{playlist_id}\?pnum=(\d+))"', first_page)
max_page = max(int(n) for _, n in page_urls)
for n in range(2, max_page + 1):
url = f'https://www.eroprofile.com/m/videos/album/{playlist_id}?pnum={n}'
yield from self._extract_from_page(
self._download_webpage(url, playlist_id,
note=f'Downloading playlist page {int(n) - 1}'))
def _real_extract(self, url):
playlist_id = self._match_id(url)
first_page = self._download_webpage(url, playlist_id, note='Downloading playlist')
playlist_title = self._search_regex(
r'<title>Album: (.*) - EroProfile</title>', first_page, 'playlist_title')
return self.playlist_result(self._entries(playlist_id, first_page), playlist_id, playlist_title)