def test_bytes(self):
for secret_key in ['secret', b'secret', 1]:
if secret_key == 1:
with self.assertRaises(TypeError):
webutils.new_hmac(secret_key, b'http://example.com')
continue
res = webutils.new_hmac(secret_key, b'http://example.com')
self.assertEqual(
res,
'23e2baa2404012a5cc8e4a18b4aabf0dde4cb9b56f679ddc0fd6d7c24339d819')
def image_proxify(url):
if url.startswith('//'):
url = 'https:' + url
if not request.preferences.get_value('image_proxy'):
return url
if url.startswith('data:image/'):
# 50 is an arbitrary number to get only the beginning of the image.
partial_base64 = url[len('data:image/'):50].split(';')
if len(partial_base64) == 2 \
and partial_base64[0] in ['gif', 'png', 'jpeg', 'pjpeg', 'webp', 'tiff', 'bmp']\
and partial_base64[1].startswith('base64,'):
return url
else:
return None
if settings.get('result_proxy'):
return proxify(url)
h = new_hmac(settings['server']['secret_key'], url.encode())
return '{0}?{1}'.format(url_for('image_proxy'),
urlencode(dict(url=url.encode(), h=h)))
def image_proxify(url):
if url.startswith("//"):
url = "https:" + url
if not request.preferences.get_value("image_proxy"):
return url
if url.startswith("data:image/"):
# 50 is an arbitrary number to get only the beginning of the image.
partial_base64 = url[len("data:image/"):50].split(";")
if (len(partial_base64) == 2 and partial_base64[0]
in ["gif", "png", "jpeg", "pjpeg", "webp", "tiff", "bmp"]
and partial_base64[1].startswith("base64,")):
return url
else:
return None
if settings.get("result_proxy"):
return proxify(url)
h = new_hmac(settings["server"]["secret_key"], url.encode())
return "{0}?{1}".format(url_for("image_proxy"),
urlencode(dict(url=url.encode(), h=h)))
def image_proxy():
url = request.args.get("url").encode()
if not url:
return "", 400
h = new_hmac(settings["server"]["secret_key"], url)
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 = requests.get(
url,
stream=True,
timeout=settings["outgoing"]["request_timeout"],
headers=headers,
proxies=get_global_proxies(),
)
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.headers.get("content-type")))
return "", 400
img = b""
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 image_proxy():
url = request.args.get('url')
if not url:
return '', 400
h = new_hmac(settings['server']['secret_key'], url.encode())
if h != request.args.get('h'):
return '', 400
maximum_size = 5 * 1024 * 1024
try:
headers = dict_subset(request.headers, {'If-Modified-Since', 'If-None-Match'})
headers['User-Agent'] = gen_useragent()
stream = http_stream(
method='GET',
url=url,
headers=headers,
timeout=settings['outgoing']['request_timeout'],
allow_redirects=True,
max_redirects=20)
resp = next(stream)
content_length = resp.headers.get('Content-Length')
if content_length and content_length.isdigit() and int(content_length) > maximum_size:
return 'Max size', 400
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.headers.get('content-type')))
return '', 400
headers = dict_subset(resp.headers, {'Content-Length', 'Length', 'Date', 'Last-Modified', 'Expires', 'Etag'})
total_length = 0
def forward_chunk():
nonlocal total_length
for chunk in stream:
total_length += len(chunk)
if total_length > maximum_size:
break
yield chunk
return Response(forward_chunk(), mimetype=resp.headers['Content-Type'], headers=headers)
except httpx.HTTPError:
return '', 400
def image_proxy():
url = request.args.get('url').encode()
if not url:
return '', 400
h = new_hmac(settings['server']['secret_key'], url)
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 = requests.get(url,
stream=True,
timeout=settings['outgoing']['request_timeout'],
headers=headers,
proxies=outgoing_proxies)
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.headers.get('content-type')))
return '', 400
img = b''
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 response(resp):
results = []
dom = html.fromstring(resp.text)
try:
results.append({'number_of_results': int(dom.xpath('//span[@class="nums_text"]/text()')[0]
.split(u'\u7ea6')[1].split(u'\u4e2a')[0].replace(',', ''))})
except Exception as e:
logger.debug('result error :\n%s', e)
# parse results
for result in dom.xpath('//div[@class="result c-container new-pmd"]'):
title = extract_text(result.xpath('.//h3/a')[0])
# when search query is Chinese words
try:
url = result.xpath('.//h3[@class="t"]/a')[0].attrib.get('href')
url = get_baidu_link_location(url)
# To generate miji url with baidu url
content = extract_text((result.xpath('.//div[@class="c-abstract"]') or
result.xpath('.//div[@class="c-abstract c-abstract-en"]')))
# append result
results.append({'url': url,'title': title,'content': content})
# when search query is English words
except Exception:
try:
url = result.xpath('.//h3[@class="t"]/a')[0].attrib.get('href')
content = extract_text(result.xpath('.//div[@class="c-span18 c-span-last"]')[0])
# To generate miji url with baidu url
url = settings['result_proxy'].get('server_name') + "/url_proxy?proxyurl=" + \
url + "&token=" + new_hmac(settings['result_proxy']['key'], url.encode("utf-8"))
# append result
results.append({'url': url,
'title': title,
'content': content})
except Exception as e:
logger.debug('result error :\n%s', e)
# return results
return results
def image_proxy():
# pylint: disable=too-many-return-statements, too-many-branches
url = request.args.get('url')
if not url:
return '', 400
h = new_hmac(settings['server']['secret_key'], url.encode())
if h != request.args.get('h'):
return '', 400
maximum_size = 5 * 1024 * 1024
forward_resp = False
resp = None
try:
request_headers = {
'User-Agent': gen_useragent(),
'Accept': 'image/webp,*/*',
'Accept-Encoding': 'gzip, deflate',
'Sec-GPC': '1',
'DNT': '1',
}
set_context_network_name('image_proxy')
stream = http_stream(method='GET',
url=url,
headers=request_headers,
timeout=settings['outgoing']['request_timeout'],
follow_redirects=True,
max_redirects=20)
resp = next(stream)
content_length = resp.headers.get('Content-Length')
if content_length and content_length.isdigit(
) and int(content_length) > maximum_size:
return 'Max size', 400
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: %s',
resp.headers.get('Content-Type', ''))
return '', 400
forward_resp = True
except httpx.HTTPError:
logger.exception('HTTP error')
return '', 400
finally:
if resp and not forward_resp:
# the code is about to return an HTTP 400 error to the browser
# we make sure to close the response between searxng and the HTTP server
try:
resp.close()
except httpx.HTTPError:
logger.exception('HTTP error on closing')
try:
headers = dict_subset(
resp.headers,
{'Content-Type', 'Content-Encoding', 'Content-Length', 'Length'})
def forward_chunk():
total_length = 0
for chunk in stream:
total_length += len(chunk)
if total_length > maximum_size:
break
yield chunk
return Response(forward_chunk(),
mimetype=resp.headers['Content-Type'],
headers=headers)
except httpx.HTTPError:
return '', 400
