-class OpenloadIE(InfoExtractor):
- _VALID_URL = r'https://openload.(?:co|io)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
-
- _TESTS = [{
- 'url': 'https://openload.co/f/kUEfGclsU9o',
- 'md5': 'bf1c059b004ebc7a256f89408e65c36e',
- 'info_dict': {
- 'id': 'kUEfGclsU9o',
- 'ext': 'mp4',
- 'title': 'skyrim_no-audio_1080.mp4',
- 'thumbnail': 're:^https?://.*\.jpg$',
- },
- }, {
- 'url': 'https://openload.co/embed/kUEfGclsU9o/skyrim_no-audio_1080.mp4',
- 'only_matching': True,
- }, {
- 'url': 'https://openload.io/f/ZAn6oz-VZGE/',
- 'only_matching': True,
- }, {
- 'url': 'https://openload.co/f/_-ztPaZtMhM/',
- 'only_matching': True,
- }, {
- # unavailable via https://openload.co/f/Sxz5sADo82g/, different layout
- # for title and ext
- 'url': 'https://openload.co/embed/Sxz5sADo82g/',
- 'only_matching': True,
- }]
-
- def _real_extract(self, url):
- video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
-
- if 'File not found' in webpage:
- raise ExtractorError('File not found', expected=True)
-
- # The following extraction logic is proposed by @Belderak and @gdkchan
- # and declared to be used freely in youtube-dl
- # See https://github.com/rg3/youtube-dl/issues/9706
-
- numbers_js = self._download_webpage(
- 'https://openload.co/assets/js/obfuscator/n.js', video_id,
- note='Downloading signature numbers')
- signums = self._search_regex(
- r'window\.signatureNumbers\s*=\s*[\'"](?P<data>[a-z]+)[\'"]',
- numbers_js, 'signature numbers', group='data')
-
- linkimg_uri = self._search_regex(
- r'<img[^>]+id="linkimg"[^>]+src="([^"]+)"', webpage, 'link image')
- linkimg = self._request_webpage(
- linkimg_uri, video_id, note=False).read()
-
- width, height, pixels = decode_png(linkimg)
-
- output = ''
- for y in range(height):
- for x in range(width):
- r, g, b = pixels[y][3 * x:3 * x + 3]
- if r == 0 and g == 0 and b == 0:
- break
- else:
- output += compat_chr(r)
- output += compat_chr(g)
- output += compat_chr(b)
-
- img_str_length = len(output) // 200
- img_str = [[0 for x in range(img_str_length)] for y in range(10)]
-
- sig_str_length = len(signums) // 260
- sig_str = [[0 for x in range(sig_str_length)] for y in range(10)]
-
- for i in range(10):
- for j in range(img_str_length):
- begin = i * img_str_length * 20 + j * 20
- img_str[i][j] = output[begin:begin + 20]
- for j in range(sig_str_length):
- begin = i * sig_str_length * 26 + j * 26
- sig_str[i][j] = signums[begin:begin + 26]
-
- parts = []
- # TODO: find better names for str_, chr_ and sum_
- str_ = ''
- for i in [2, 3, 5, 7]:
- str_ = ''
- sum_ = float(99)
- for j in range(len(sig_str[i])):
- for chr_idx in range(len(img_str[i][j])):
- if sum_ > float(122):
- sum_ = float(98)
- chr_ = compat_chr(int(math.floor(sum_)))
- if sig_str[i][j][chr_idx] == chr_ and j >= len(str_):
- sum_ += float(2.5)
- str_ += img_str[i][j][chr_idx]
- parts.append(str_.replace(',', ''))
-
- video_url = 'https://openload.co/stream/%s~%s~%s~%s' % (parts[3], parts[1], parts[2], parts[0])
-
- title = self._og_search_title(webpage, default=None) or self._search_regex(
- r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
- 'title', default=None) or self._html_search_meta(
- 'description', webpage, 'title', fatal=True)
-
- return {
- 'id': video_id,
- 'title': title,
- 'thumbnail': self._og_search_thumbnail(webpage, default=None),
- 'url': video_url,
- # Seems all videos have extensions in their titles
- 'ext': determine_ext(title),
+def cookie_to_dict(cookie):
+ cookie_dict = {
+ 'name': cookie.name,
+ 'value': cookie.value,
+ }
+ if cookie.port_specified:
+ cookie_dict['port'] = cookie.port
+ if cookie.domain_specified:
+ cookie_dict['domain'] = cookie.domain
+ if cookie.path_specified:
+ cookie_dict['path'] = cookie.path
+ if cookie.expires is not None:
+ cookie_dict['expires'] = cookie.expires
+ if cookie.secure is not None:
+ cookie_dict['secure'] = cookie.secure
+ if cookie.discard is not None:
+ cookie_dict['discard'] = cookie.discard
+ try:
+ if (cookie.has_nonstandard_attr('httpOnly')
+ or cookie.has_nonstandard_attr('httponly')
+ or cookie.has_nonstandard_attr('HttpOnly')):
+ cookie_dict['httponly'] = True
+ except TypeError:
+ pass
+ return cookie_dict
+
+
+def cookie_jar_to_list(cookie_jar):
+ return [cookie_to_dict(cookie) for cookie in cookie_jar]
+
+
+class PhantomJSwrapper(object):
+ """PhantomJS wrapper class
+
+ This class is experimental.
+ """
+
+ _TEMPLATE = r'''
+ phantom.onError = function(msg, trace) {{
+ var msgStack = ['PHANTOM ERROR: ' + msg];
+ if(trace && trace.length) {{
+ msgStack.push('TRACE:');
+ trace.forEach(function(t) {{
+ msgStack.push(' -> ' + (t.file || t.sourceURL) + ': ' + t.line
+ + (t.function ? ' (in function ' + t.function +')' : ''));
+ }});
+ }}
+ console.error(msgStack.join('\n'));
+ phantom.exit(1);
+ }};
+ var page = require('webpage').create();
+ var fs = require('fs');
+ var read = {{ mode: 'r', charset: 'utf-8' }};
+ var write = {{ mode: 'w', charset: 'utf-8' }};
+ JSON.parse(fs.read("{cookies}", read)).forEach(function(x) {{
+ phantom.addCookie(x);
+ }});
+ page.settings.resourceTimeout = {timeout};
+ page.settings.userAgent = "{ua}";
+ page.onLoadStarted = function() {{
+ page.evaluate(function() {{
+ delete window._phantom;
+ delete window.callPhantom;
+ }});
+ }};
+ var saveAndExit = function() {{
+ fs.write("{html}", page.content, write);
+ fs.write("{cookies}", JSON.stringify(phantom.cookies), write);
+ phantom.exit();
+ }};
+ page.onLoadFinished = function(status) {{
+ if(page.url === "") {{
+ page.setContent(fs.read("{html}", read), "{url}");
+ }}
+ else {{
+ {jscode}
+ }}
+ }};
+ page.open("");
+ '''
+
+ _TMP_FILE_NAMES = ['script', 'html', 'cookies']
+
+ @staticmethod
+ def _version():
+ return get_exe_version('phantomjs', version_re=r'([0-9.]+)')
+
+ def __init__(self, extractor, required_version=None, timeout=10000):
+ self._TMP_FILES = {}
+
+ self.exe = check_executable('phantomjs', ['-v'])
+ if not self.exe:
+ raise ExtractorError('PhantomJS executable not found in PATH, '
+ 'download it from http://phantomjs.org',
+ expected=True)
+
+ self.extractor = extractor
+
+ if required_version:
+ version = self._version()
+ if is_outdated_version(version, required_version):
+ self.extractor._downloader.report_warning(
+ 'Your copy of PhantomJS is outdated, update it to version '
+ '%s or newer if you encounter any errors.' % required_version)
+
+ self.options = {
+ 'timeout': timeout,
Rapsys Git / youtubedl / blobdiff