diff --git a/bin/async_capture.py b/bin/async_capture.py
index c42775b..43ed7a5 100755
--- a/bin/async_capture.py
+++ b/bin/async_capture.py
@@ -58,6 +58,17 @@ class AsyncCapture(AbstractManager):
# By default, the captures are not on the index, unless the user mark them as listed
listing = True if ('listing' in to_capture and to_capture['listing'].lower() in ['true', '1']) else False
+ # Turn the freetext for the headers into a dict
+ headers = {}
+ if 'headers' in to_capture:
+ for header_line in to_capture['headers'].splitlines():
+ if header_line and ':' in header_line:
+ splitted = header_line.split(':', 1)
+ if splitted and len(splitted) == 2:
+ header, h_value = splitted
+ if header and h_value:
+ headers[header.strip()] = h_value.strip()
+
self.logger.info(f'Capturing {to_capture["url"]} - {uuid}')
success, error_message = self._capture(
to_capture['url'],
@@ -67,6 +78,7 @@ class AsyncCapture(AbstractManager):
listing=listing,
user_agent=to_capture.get('user_agent', None),
referer=to_capture.get('referer', None),
+ headers=headers if headers else None,
proxy=to_capture.get('proxy', None),
os=to_capture.get('os', None),
browser=to_capture.get('browser', None),
@@ -85,7 +97,7 @@ class AsyncCapture(AbstractManager):
def _capture(self, url: str, *, perma_uuid: str, cookies_pseudofile: Optional[Union[BufferedIOBase, str]]=None,
depth: int=1, listing: bool=True, user_agent: Optional[str]=None,
- referer: Optional[str]=None, proxy: Optional[str]=None, os: Optional[str]=None,
+ referer: Optional[str]=None, headers: Optional[Dict[str, str]]=None, proxy: Optional[str]=None, os: Optional[str]=None,
browser: Optional[str]=None, parent: Optional[str]=None) -> Tuple[bool, str]:
'''Launch a capture'''
url = url.strip()
@@ -120,14 +132,15 @@ class AsyncCapture(AbstractManager):
self.logger.info(f'Capturing {url}')
try:
items = crawl(self.splash_url, url, cookies=cookies, depth=depth, user_agent=ua,
- referer=referer, proxy=proxy, log_enabled=True, log_level=get_config('generic', 'splash_loglevel'))
+ referer=referer, headers=headers, proxy=proxy, log_enabled=True,
+ log_level=get_config('generic', 'splash_loglevel'))
except Exception as e:
self.logger.critical(f'Something went terribly wrong when capturing {url}.')
raise e
if not items:
# broken
self.logger.critical(f'Something went terribly wrong when capturing {url}.')
- return False, 'Something went terribly wrong when capturing {url}.'
+ return False, f'Something went terribly wrong when capturing {url}.'
width = len(str(len(items)))
now = datetime.now()
dirpath = self.capture_dir / str(now.year) / f'{now.month:02}' / now.isoformat()
diff --git a/poetry.lock b/poetry.lock
index 5229d1d..c598122 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -1069,7 +1069,7 @@ python-versions = "*"
[[package]]
name = "scrapysplashwrapper"
-version = "1.9.2"
+version = "1.9.3"
description = "Scrapy splash wrapper as a standalone library."
category = "main"
optional = false
@@ -1080,7 +1080,7 @@ Scrapy = ">=2.5.1,<3.0.0"
scrapy-splash = ">=0.8.0,<0.9.0"
[package.extras]
-docs = ["Sphinx (>=4.2.0,<5.0.0)"]
+docs = ["Sphinx (>=4.3.0,<5.0.0)"]
[[package]]
name = "service-identity"
@@ -1183,7 +1183,7 @@ python-versions = "*"
[[package]]
name = "types-click"
-version = "7.1.7"
+version = "7.1.8"
description = "Typing stubs for click"
category = "dev"
optional = false
@@ -1231,7 +1231,7 @@ python-versions = "*"
[[package]]
name = "types-redis"
-version = "3.5.17"
+version = "3.5.18"
description = "Typing stubs for redis"
category = "dev"
optional = false
@@ -1247,7 +1247,7 @@ python-versions = "*"
[[package]]
name = "types-werkzeug"
-version = "1.0.7"
+version = "1.0.8"
description = "Typing stubs for Werkzeug"
category = "dev"
optional = false
@@ -1357,7 +1357,7 @@ misp = ["python-magic", "pydeep"]
[metadata]
lock-version = "1.1"
python-versions = ">=3.8,<3.11"
-content-hash = "19237996db1901ec730199fe80f3a6ecaa58d5c1472429165c49a0770218f188"
+content-hash = "e74e1a05ff00a1cec28efc8ee00fb90318684d682e825ad67da9a6d10a9f8975"
[metadata.files]
aiohttp = [
@@ -2308,8 +2308,8 @@ scrapy-splash = [
{file = "scrapy_splash-0.8.0-py2.py3-none-any.whl", hash = "sha256:f35986fbe916d4b7878f4d303ca6a9d4f013157ab2bae13d85f14da78d211193"},
]
scrapysplashwrapper = [
- {file = "scrapysplashwrapper-1.9.2-py3-none-any.whl", hash = "sha256:ca63c67c0892ac1ab1a9db5c3e83711b7683306571a08fbfba43d9b71d55f826"},
- {file = "scrapysplashwrapper-1.9.2.tar.gz", hash = "sha256:3edb2860a35c4cf74e13c377130ebda777498e7f576e9b6aca2dd7b268d85934"},
+ {file = "scrapysplashwrapper-1.9.3-py3-none-any.whl", hash = "sha256:ece1dbf0ec4c0b9fe34f34bc063ae27592cd89fe2d205c2c476514baf4b1c372"},
+ {file = "scrapysplashwrapper-1.9.3.tar.gz", hash = "sha256:0621a02fffba2d9eab8e0bea3e986474b3d9edfcd5681f41a8162c8bba517490"},
]
service-identity = [
{file = "service-identity-21.1.0.tar.gz", hash = "sha256:6e6c6086ca271dc11b033d17c3a8bea9f24ebff920c587da090afc9519419d34"},
@@ -2350,8 +2350,8 @@ twisted-iocpsupport = [
{file = "twisted_iocpsupport-1.0.2-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:7d972cfa8439bdcb35a7be78b7ef86d73b34b808c74be56dfa785c8a93b851bf"},
]
types-click = [
- {file = "types-click-7.1.7.tar.gz", hash = "sha256:fff7ea52619581401a90cb9247e1a7e95c29084cfdbc26b7a49ed94c40fcd3d8"},
- {file = "types_click-7.1.7-py3-none-any.whl", hash = "sha256:64dd3dc1fe5ed7e105b7a0479a6aebdd3c132c474c54f42a744af1bfba1989fd"},
+ {file = "types-click-7.1.8.tar.gz", hash = "sha256:b6604968be6401dc516311ca50708a0a28baa7a0cb840efd7412f0dbbff4e092"},
+ {file = "types_click-7.1.8-py3-none-any.whl", hash = "sha256:8cb030a669e2e927461be9827375f83c16b8178c365852c060a34e24871e7e81"},
]
types-flask = [
{file = "types-Flask-1.1.5.tar.gz", hash = "sha256:1294df1615e01135c5dbba530e3f8d58918afa6796f1dee8b2143c7dd47b7970"},
@@ -2370,16 +2370,16 @@ types-pkg-resources = [
{file = "types_pkg_resources-0.1.3-py2.py3-none-any.whl", hash = "sha256:0cb9972cee992249f93fff1a491bf2dc3ce674e5a1926e27d4f0866f7d9b6d9c"},
]
types-redis = [
- {file = "types-redis-3.5.17.tar.gz", hash = "sha256:79a95e3da407fe8a6f227ce29e3ca6e4a235fd30331e1a599879d3c9258291ff"},
- {file = "types_redis-3.5.17-py3-none-any.whl", hash = "sha256:f267bcbc2f0c30af72de334ceb644c3694efc69f0b9131f3f359cf824ed8d079"},
+ {file = "types-redis-3.5.18.tar.gz", hash = "sha256:15482304e8848c63b383b938ffaba7ebe0b7f8f33381ecc450ee03935213e166"},
+ {file = "types_redis-3.5.18-py3-none-any.whl", hash = "sha256:5c55c4b9e8ebdc6d57d4e47900b77d99f19ca0a563264af3f701246ed0926335"},
]
types-requests = [
{file = "types-requests-2.26.0.tar.gz", hash = "sha256:df5ec8c34b413a42ebb38e4f96bdeb68090b875bdfcc5138dc82989c95445883"},
{file = "types_requests-2.26.0-py3-none-any.whl", hash = "sha256:809b5dcd3c408ac39d11d593835b6aff32420b3e7ddb79c7f3e823330f040466"},
]
types-werkzeug = [
- {file = "types-Werkzeug-1.0.7.tar.gz", hash = "sha256:2e8779fd17856ce4e2cc7eeb1446bfb9afc43fd1a5b067265a4f13d6f7f68499"},
- {file = "types_Werkzeug-1.0.7-py3-none-any.whl", hash = "sha256:dc0972040f0f043b813ab574079b0b101a44d434d67bf1695afffc6b0aad0362"},
+ {file = "types-Werkzeug-1.0.8.tar.gz", hash = "sha256:310f06032b71c28c7ae2b189b44d52c29e1a667e87c2e9e8405761b01cb83859"},
+ {file = "types_Werkzeug-1.0.8-py3-none-any.whl", hash = "sha256:212e8e0da7b205b159d70eaf1121a8cef08ee7a7eeae83406379045d3385078d"},
]
typing-extensions = [
{file = "typing_extensions-4.0.0-py3-none-any.whl", hash = "sha256:829704698b22e13ec9eaf959122315eabb370b0884400e9818334d8b677023d9"},
diff --git a/pyproject.toml b/pyproject.toml
index 00869c5..55b60b9 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -46,7 +46,7 @@ bootstrap-flask = "^1.8.0"
defang = "^0.5.3"
vt-py = "^0.8.0"
pyeupi = "^1.1"
-scrapysplashwrapper = "^1.9.2"
+scrapysplashwrapper = "^1.9.3"
pysanejs = "^2.0"
har2tree = "^1.9.1"
pylookyloo = "^1.9"
diff --git a/website/web/__init__.py b/website/web/__init__.py
index 21d9d60..87c507b 100644
--- a/website/web/__init__.py
+++ b/website/web/__init__.py
@@ -846,6 +846,9 @@ def capture_web():
if request.form.get('referer'):
capture_query['referer'] = request.form['referer']
+ if request.form.get('headers'):
+ capture_query['headers'] = request.form['headers']
+
if request.form.get('proxy'):
parsed_proxy = urlparse(request.form['proxy'])
if parsed_proxy.scheme and parsed_proxy.hostname and parsed_proxy.port:
diff --git a/website/web/genericapi.py b/website/web/genericapi.py
index cf34d20..de6ffb2 100644
--- a/website/web/genericapi.py
+++ b/website/web/genericapi.py
@@ -322,6 +322,7 @@ submit_fields_post = api.model('SubmitFieldsPost', {
'listing': fields.Integer(description="Display the capture on the index", min=0, max=1, example=1),
'user_agent': fields.String(description="User agent to use for the capture", example=''),
'referer': fields.String(description="Referer to pass to the capture", example=''),
+ 'headers': fields.String(description="Referer to pass to the capture", example='Accept-Language: en-US;q=0.5, fr-FR;q=0.4'),
'proxy': fields.Url(description="Proxy to use for the capture. Format: [scheme]://[username]:[password]@[hostname]:[port]", example=''),
'cookies': fields.String(description="JSON export of a list of cookies as exported from an other capture", example='')
})
@@ -351,6 +352,8 @@ class SubmitCapture(Resource):
to_query['user_agent'] = request.args['user_agent']
if request.args.get('referer'):
to_query['referer'] = request.args['referer']
+ if request.args.get('headers'):
+ to_query['headers'] = request.args['headers']
if request.args.get('proxy'):
to_query['proxy'] = request.args['proxy']
diff --git a/website/web/templates/capture.html b/website/web/templates/capture.html
index fb718f8..71585ab 100644
--- a/website/web/templates/capture.html
+++ b/website/web/templates/capture.html
@@ -84,6 +84,13 @@
+
+