]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/openload.py
2 from __future__
import unicode_literals
10 from .common
import InfoExtractor
11 from ..compat
import (
27 def cookie_to_dict(cookie
):
30 'value': cookie
.value
,
32 if cookie
.port_specified
:
33 cookie_dict
['port'] = cookie
.port
34 if cookie
.domain_specified
:
35 cookie_dict
['domain'] = cookie
.domain
36 if cookie
.path_specified
:
37 cookie_dict
['path'] = cookie
.path
38 if cookie
.expires
is not None:
39 cookie_dict
['expires'] = cookie
.expires
40 if cookie
.secure
is not None:
41 cookie_dict
['secure'] = cookie
.secure
42 if cookie
.discard
is not None:
43 cookie_dict
['discard'] = cookie
.discard
45 if (cookie
.has_nonstandard_attr('httpOnly') or
46 cookie
.has_nonstandard_attr('httponly') or
47 cookie
.has_nonstandard_attr('HttpOnly')):
48 cookie_dict
['httponly'] = True
54 def cookie_jar_to_list(cookie_jar
):
55 return [cookie_to_dict(cookie
) for cookie
in cookie_jar
]
58 class PhantomJSwrapper(object):
59 """PhantomJS wrapper class
61 This class is experimental.
65 phantom.onError = function(msg, trace) {{
66 var msgStack = ['PHANTOM ERROR: ' + msg];
67 if(trace && trace.length) {{
68 msgStack.push('TRACE:');
69 trace.forEach(function(t) {{
70 msgStack.push(' -> ' + (t.file || t.sourceURL) + ': ' + t.line
71 + (t.function ? ' (in function ' + t.function +')' : ''));
74 console.error(msgStack.join('\n'));
77 var page = require('webpage').create();
78 var fs = require('fs');
79 var read = {{ mode: 'r', charset: 'utf-8' }};
80 var write = {{ mode: 'w', charset: 'utf-8' }};
81 JSON.parse(fs.read("{cookies}", read)).forEach(function(x) {{
84 page.settings.resourceTimeout = {timeout};
85 page.settings.userAgent = "{ua}";
86 page.onLoadStarted = function() {{
87 page.evaluate(function() {{
88 delete window._phantom;
89 delete window.callPhantom;
92 var saveAndExit = function() {{
93 fs.write("{html}", page.content, write);
94 fs.write("{cookies}", JSON.stringify(phantom.cookies), write);
97 page.onLoadFinished = function(status) {{
98 if(page.url === "") {{
99 page.setContent(fs.read("{html}", read), "{url}");
108 _TMP_FILE_NAMES
= ['script', 'html', 'cookies']
112 return get_exe_version('phantomjs', version_re
=r
'([0-9.]+)')
114 def __init__(self
, extractor
, required_version
=None, timeout
=10000):
117 self
.exe
= check_executable('phantomjs', ['-v'])
119 raise ExtractorError('PhantomJS executable not found in PATH, '
120 'download it from http://phantomjs.org',
123 self
.extractor
= extractor
126 version
= self
._version
()
127 if is_outdated_version(version
, required_version
):
128 self
.extractor
._downloader
.report_warning(
129 'Your copy of PhantomJS is outdated, update it to version '
130 '%s or newer if you encounter any errors.' % required_version
)
135 for name
in self
._TMP
_FILE
_NAMES
:
136 tmp
= tempfile
.NamedTemporaryFile(delete
=False)
138 self
._TMP
_FILES
[name
] = tmp
141 for name
in self
._TMP
_FILE
_NAMES
:
143 os
.remove(self
._TMP
_FILES
[name
].name
)
144 except (IOError, OSError, KeyError):
147 def _save_cookies(self
, url
):
148 cookies
= cookie_jar_to_list(self
.extractor
._downloader
.cookiejar
)
149 for cookie
in cookies
:
150 if 'path' not in cookie
:
152 if 'domain' not in cookie
:
153 cookie
['domain'] = compat_urlparse
.urlparse(url
).netloc
154 with open(self
._TMP
_FILES
['cookies'].name
, 'wb') as f
:
155 f
.write(json
.dumps(cookies
).encode('utf-8'))
157 def _load_cookies(self
):
158 with open(self
._TMP
_FILES
['cookies'].name
, 'rb') as f
:
159 cookies
= json
.loads(f
.read().decode('utf-8'))
160 for cookie
in cookies
:
161 if cookie
['httponly'] is True:
162 cookie
['rest'] = {'httpOnly': None}
163 if 'expiry' in cookie
:
164 cookie
['expire_time'] = cookie
['expiry']
165 self
.extractor
._set
_cookie
(**compat_kwargs(cookie
))
167 def get(self
, url
, html
=None, video_id
=None, note
=None, note2
='Executing JS on webpage', headers
={}, jscode
='saveAndExit();'):
169 Downloads webpage (if needed) and executes JS
173 html: optional, html code of website
175 note: optional, displayed when downloading webpage
176 note2: optional, displayed when executing JS
177 headers: custom http headers
178 jscode: code to be executed when page is loaded
181 * downloaded website (after JS execution)
182 * anything you print with `console.log` (but not inside `page.execute`!)
184 In most cases you don't need to add any `jscode`.
185 It is executed in `page.onLoadFinished`.
186 `saveAndExit();` is mandatory, use it instead of `phantom.exit()`
187 It is possible to wait for some element on the webpage, for example:
188 var check = function() {
189 var elementFound = page.evaluate(function() {
190 return document.querySelector('#b.done') !== null;
195 window.setTimeout(check, 500);
198 page.evaluate(function(){
199 document.querySelector('#a').click();
203 if 'saveAndExit();' not in jscode
:
204 raise ExtractorError('`saveAndExit();` not found in `jscode`')
206 html
= self
.extractor
._download
_webpage
(url
, video_id
, note
=note
, headers
=headers
)
207 with open(self
._TMP
_FILES
['html'].name
, 'wb') as f
:
208 f
.write(html
.encode('utf-8'))
210 self
._save
_cookies
(url
)
212 replaces
= self
.options
213 replaces
['url'] = url
214 user_agent
= headers
.get('User-Agent') or std_headers
['User-Agent']
215 replaces
['ua'] = user_agent
.replace('"', '\\"')
216 replaces
['jscode'] = jscode
218 for x
in self
._TMP
_FILE
_NAMES
:
219 replaces
[x
] = self
._TMP
_FILES
[x
].name
.replace('\\', '\\\\').replace('"', '\\"')
221 with open(self
._TMP
_FILES
['script'].name
, 'wb') as f
:
222 f
.write(self
._TEMPLATE
.format(**replaces
).encode('utf-8'))
225 self
.extractor
.to_screen('%s' % (note2
,))
227 self
.extractor
.to_screen('%s: %s' % (video_id
, note2
))
229 p
= subprocess
.Popen([
230 self
.exe
, '--ssl-protocol=any',
231 self
._TMP
_FILES
['script'].name
232 ], stdout
=subprocess
.PIPE
, stderr
=subprocess
.PIPE
)
233 out
, err
= p
.communicate()
234 if p
.returncode
!= 0:
235 raise ExtractorError(
236 'Executing JS failed\n:' + encodeArgument(err
))
237 with open(self
._TMP
_FILES
['html'].name
, 'rb') as f
:
238 html
= f
.read().decode('utf-8')
242 return (html
, encodeArgument(out
))
245 class OpenloadIE(InfoExtractor
):
246 _VALID_URL
= r
'''(?x)
251 openload\.(?:co|io|link)|
252 oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun)
256 (?P<id>[a-zA-Z0-9-_]+)
260 'url': 'https://openload.co/f/kUEfGclsU9o',
261 'md5': 'bf1c059b004ebc7a256f89408e65c36e',
265 'title': 'skyrim_no-audio_1080.mp4',
266 'thumbnail': r
're:^https?://.*\.jpg$',
269 'url': 'https://openload.co/embed/rjC09fkPLYs',
273 'title': 'movie.mp4',
274 'thumbnail': r
're:^https?://.*\.jpg$',
282 'skip_download': True, # test subtitles only
285 'url': 'https://openload.co/embed/kUEfGclsU9o/skyrim_no-audio_1080.mp4',
286 'only_matching': True,
288 'url': 'https://openload.io/f/ZAn6oz-VZGE/',
289 'only_matching': True,
291 'url': 'https://openload.co/f/_-ztPaZtMhM/',
292 'only_matching': True,
294 # unavailable via https://openload.co/f/Sxz5sADo82g/, different layout
296 'url': 'https://openload.co/embed/Sxz5sADo82g/',
297 'only_matching': True,
299 # unavailable via https://openload.co/embed/e-Ixz9ZR5L0/ but available
300 # via https://openload.co/f/e-Ixz9ZR5L0/
301 'url': 'https://openload.co/f/e-Ixz9ZR5L0/',
302 'only_matching': True,
304 'url': 'https://oload.tv/embed/KnG-kKZdcfY/',
305 'only_matching': True,
307 'url': 'http://www.openload.link/f/KnG-kKZdcfY',
308 'only_matching': True,
310 'url': 'https://oload.stream/f/KnG-kKZdcfY',
311 'only_matching': True,
313 'url': 'https://oload.xyz/f/WwRBpzW8Wtk',
314 'only_matching': True,
316 'url': 'https://oload.win/f/kUEfGclsU9o',
317 'only_matching': True,
319 'url': 'https://oload.download/f/kUEfGclsU9o',
320 'only_matching': True,
322 'url': 'https://oload.cloud/f/4ZDnBXRWiB8',
323 'only_matching': True,
325 # Its title has not got its extension but url has it
326 'url': 'https://oload.download/f/N4Otkw39VCw/Tomb.Raider.2018.HDRip.XviD.AC3-EVO.avi.mp4',
327 'only_matching': True,
329 'url': 'https://oload.cc/embed/5NEAbI2BDSk',
330 'only_matching': True,
332 'url': 'https://oload.icu/f/-_i4y_F_Hs8',
333 'only_matching': True,
335 'url': 'https://oload.fun/f/gb6G1H4sHXY',
336 'only_matching': True,
339 _USER_AGENT
= 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
342 def _extract_urls(webpage
):
344 r
'<iframe[^>]+src=["\']((?
:https?
://)?
(?
:openload\
.(?
:co|io
)|oload\
.tv
)/embed
/[a
-zA
-Z0
-9-_
]+)',
347 def _real_extract(self, url):
348 mobj = re.match(self._VALID_URL, url)
349 host = mobj.group('host
')
350 video_id = mobj.group('id')
352 url_pattern = 'https
://%s/%%s/%s/' % (host, video_id)
354 'User
-Agent
': self._USER_AGENT,
357 for path in ('embed
', 'f
'):
358 page_url = url_pattern % path
360 webpage = self._download_webpage(
361 page_url, video_id, 'Downloading
%s webpage
' % path,
362 headers=headers, fatal=last)
365 if 'File
not found
' in webpage or 'deleted by the owner
' in webpage:
368 raise ExtractorError('File
not found
', expected=True, video_id=video_id)
371 phantom = PhantomJSwrapper(self, required_version='2.0')
372 webpage, _ = phantom.get(page_url, html=webpage, video_id=video_id, headers=headers)
374 decoded_id = (get_element_by_id('streamurl
', webpage) or
375 get_element_by_id('streamuri
', webpage) or
376 get_element_by_id('streamurj
', webpage) or
378 (r'>\s
*([\w
-]+~\d
{10,}~\d
+\
.\d
+\
.0\
.0~
[\w
-]+)\s
*<',
379 r'>\s
*([\w~
-]+~\d
+\
.\d
+\
.\d
+\
.\d
+~
[\w~
-]+)',
380 r'>\s
*([\w
-]+~\d
{10,}~
(?
:[a
-f\d
]+:){2}
:~
[\w
-]+)\s
*<',
381 r'>\s
*([\w~
-]+~
[a
-f0
-9:]+~
[\w~
-]+)\s
*<',
382 r'>\s
*([\w~
-]+~
[a
-f0
-9:]+~
[\w~
-]+)'), webpage,
385 video_url = 'https
://%s/stream
/%s?mime
=true
' % (host, decoded_id)
387 title = self._og_search_title(webpage, default=None) or self._search_regex(
388 r'<span
[^
>]+class=["\']title["\'][^
>]*>([^
<]+)', webpage,
389 'title
', default=None) or self._html_search_meta(
390 'description
', webpage, 'title
', fatal=True)
392 entries = self._parse_html5_media_entries(page_url, webpage, video_id)
393 entry = entries[0] if entries else {}
394 subtitles = entry.get('subtitles
')
399 'thumbnail
': entry.get('thumbnail
') or self._og_search_thumbnail(webpage, default=None),
401 'ext
': determine_ext(title, None) or determine_ext(url, 'mp4
'),
402 'subtitles
': subtitles,
403 'http_headers
': headers,