def get_client_id():
response = http_get("https://soundcloud.com")
rx_namespace = {"re": "http://exslt.org/regular-expressions"}
if response.ok:
tree = etree.parse(StringIO(response.content), etree.HTMLParser())
script_tags = tree.xpath("//script[re:match(@src, '(.*app.*js)')]",
namespaces=rx_namespace)
app_js_urls = [
script_tag.get('src') for script_tag in script_tags
if script_tag is not None
]
# extracts valid app_js urls from soundcloud.com content
for app_js_url in app_js_urls:
# gets app_js and searches for the clientid
response = http_get(app_js_url)
if response.ok:
cids = re.search(r'client_id:"([^"]*)"', response.content,
re.M | re.I)
if cids is not None and len(cids.groups()):
return cids.groups()[0]
logger.warning(
"Unable to fetch guest client_id from SoundCloud, check parser!")
return ""
def init(engine_settings=None):
global cookies
# initial cookies
resp = http_get(url, allow_redirects=False)
if resp.ok:
for r in resp.history:
cookies.update(r.cookies)
cookies.update(resp.cookies)
def obtain_token():
update_time = time() - (time() % 3600)
try:
token_response = http_get('https://www.wolframalpha.com/input/api/v1/code?ts=9999999999999999999', timeout=2.0)
token['value'] = loads(token_response.text)['code']
token['last_updated'] = update_time
except:
pass
return token
def obtain_token():
update_time = time() - (time() % 3600)
try:
token_response = http_get('https://www.wolframalpha.com/input/api/v1/code?ts=9999999999999999999', timeout=2.0)
token['value'] = loads(token_response.text)['code']
token['last_updated'] = update_time
except:
pass
return token
def get_client_id():
response = http_get("https://soundcloud.com")
if response.ok:
tree = html.fromstring(response.content)
script_tags = tree.xpath("//script[contains(@src, '/assets/app')]")
app_js_urls = [script_tag.get('src') for script_tag in script_tags if script_tag is not None]
# extracts valid app_js urls from soundcloud.com content
for app_js_url in app_js_urls:
# gets app_js and searches for the clientid
response = http_get(app_js_url)
if response.ok:
cids = cid_re.search(response.text)
if cids is not None and len(cids.groups()):
return cids.groups()[0]
logger.warning("Unable to fetch guest client_id from SoundCloud, check parser!")
return ""
def get_client_id():
response = http_get("https://soundcloud.com")
rx_namespace = {"re": "http://exslt.org/regular-expressions"}
if response.ok:
tree = etree.parse(StringIO(response.content), etree.HTMLParser())
script_tags = tree.xpath("//script[re:match(@src, '(.*app.*js)')]", namespaces=rx_namespace)
app_js_urls = [script_tag.get('src') for script_tag in script_tags if script_tag is not None]
# extracts valid app_js urls from soundcloud.com content
for app_js_url in app_js_urls:
# gets app_js and searches for the clientid
response = http_get(app_js_url)
if response.ok:
cids = re.search(r'client_id:"([^"]*)"', response.content, re.M | re.I)
if cids is not None and len(cids.groups()):
return cids.groups()[0]
logger.warning("Unable to fetch guest client_id from SoundCloud, check parser!")
return ""
def get_client_id():
response = http_get("https://soundcloud.com")
if response.ok:
tree = html.fromstring(response.content)
# script_tags has been moved from /assets/app/ to /assets/ path. I
# found client_id in https://a-v2.sndcdn.com/assets/49-a0c01933-3.js
script_tags = tree.xpath("//script[contains(@src, '/assets/')]")
app_js_urls = [
script_tag.get('src') for script_tag in script_tags
if script_tag is not None
]
# extracts valid app_js urls from soundcloud.com content
for app_js_url in app_js_urls:
# gets app_js and searches for the clientid
response = http_get(app_js_url)
if response.ok:
cids = cid_re.search(response.content.decode("utf-8"))
if cids is not None and len(cids.groups()):
return cids.groups()[0]
logger.warning(
"Unable to fetch guest client_id from SoundCloud, check parser!")
return ""
def image_proxy():
url = request.args.get('url')
if not url:
return '', 400
h = hashlib.sha256(url + settings['server']['secret_key']).hexdigest()
if h != request.args.get('h'):
return '', 400
headers = dict_subset(request.headers, {'If-Modified-Since', 'If-None-Match'})
headers['User-Agent'] = gen_useragent()
resp = http_get(url,
stream=True,
timeout=settings['server'].get('request_timeout', 2),
headers=headers)
if resp.status_code == 304:
return '', resp.status_code
if resp.status_code != 200:
logger.debug('image-proxy: wrong response code: {0}'.format(resp.status_code))
if resp.status_code >= 400:
return '', resp.status_code
return '', 400
if not resp.headers.get('content-type', '').startswith('image/'):
logger.debug('image-proxy: wrong content-type: {0}'.format(resp.get('content-type')))
return '', 400
img = ''
chunk_counter = 0
for chunk in resp.iter_content(1024*1024):
chunk_counter += 1
if chunk_counter > 5:
return '', 502 # Bad gateway - file is too big (>5M)
img += chunk
headers = dict_subset(resp.headers, {'Content-Length', 'Length', 'Date', 'Last-Modified', 'Expires', 'Etag'})
return Response(img, mimetype=resp.headers['content-type'], headers=headers)
def get(*args, **kwargs):
if 'timeout' not in kwargs:
kwargs['timeout'] = settings['outgoing']['request_timeout']
return http_get(*args, **kwargs)
def get(*args, **kwargs):
if 'timeout' not in kwargs:
kwargs['timeout'] = settings['outgoing']['request_timeout']
return http_get(*args, **kwargs)
def get(*args, **kwargs):
if 'timeout' not in kwargs:
kwargs['timeout'] = settings['outgoing']['request_timeout']
kwargs['raise_for_httperror'] = True
return http_get(*args, **kwargs)