scrapling 0.2.99__py3-none-any.whl → 0.3.1__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- scrapling/__init__.py +18 -31
- scrapling/cli.py +818 -20
- scrapling/core/_html_utils.py +348 -0
- scrapling/core/_types.py +34 -17
- scrapling/core/ai.py +611 -0
- scrapling/core/custom_types.py +183 -100
- scrapling/core/mixins.py +27 -19
- scrapling/core/shell.py +647 -0
- scrapling/core/{storage_adaptors.py → storage.py} +41 -33
- scrapling/core/translator.py +20 -26
- scrapling/core/utils.py +49 -54
- scrapling/engines/__init__.py +15 -6
- scrapling/engines/_browsers/__init__.py +2 -0
- scrapling/engines/_browsers/_camoufox.py +759 -0
- scrapling/engines/_browsers/_config_tools.py +130 -0
- scrapling/engines/_browsers/_controllers.py +644 -0
- scrapling/engines/_browsers/_page.py +93 -0
- scrapling/engines/_browsers/_validators.py +170 -0
- scrapling/engines/constants.py +101 -88
- scrapling/engines/static.py +667 -110
- scrapling/engines/toolbelt/__init__.py +20 -6
- scrapling/engines/toolbelt/bypasses/playwright_fingerprint.js +2 -1
- scrapling/engines/toolbelt/convertor.py +254 -0
- scrapling/engines/toolbelt/custom.py +158 -175
- scrapling/engines/toolbelt/fingerprints.py +32 -46
- scrapling/engines/toolbelt/navigation.py +68 -39
- scrapling/fetchers.py +239 -333
- scrapling/parser.py +781 -449
- scrapling-0.3.1.dist-info/METADATA +411 -0
- scrapling-0.3.1.dist-info/RECORD +41 -0
- {scrapling-0.2.99.dist-info → scrapling-0.3.1.dist-info}/WHEEL +1 -1
- {scrapling-0.2.99.dist-info → scrapling-0.3.1.dist-info}/top_level.txt +0 -1
- scrapling/defaults.py +0 -25
- scrapling/engines/camo.py +0 -339
- scrapling/engines/pw.py +0 -465
- scrapling/engines/toolbelt/bypasses/pdf_viewer.js +0 -5
- scrapling-0.2.99.dist-info/METADATA +0 -290
- scrapling-0.2.99.dist-info/RECORD +0 -49
- tests/__init__.py +0 -1
- tests/fetchers/__init__.py +0 -1
- tests/fetchers/async/__init__.py +0 -0
- tests/fetchers/async/test_camoufox.py +0 -97
- tests/fetchers/async/test_httpx.py +0 -85
- tests/fetchers/async/test_playwright.py +0 -101
- tests/fetchers/sync/__init__.py +0 -0
- tests/fetchers/sync/test_camoufox.py +0 -70
- tests/fetchers/sync/test_httpx.py +0 -84
- tests/fetchers/sync/test_playwright.py +0 -89
- tests/fetchers/test_utils.py +0 -97
- tests/parser/__init__.py +0 -0
- tests/parser/test_automatch.py +0 -111
- tests/parser/test_general.py +0 -330
- {scrapling-0.2.99.dist-info → scrapling-0.3.1.dist-info}/entry_points.txt +0 -0
- {scrapling-0.2.99.dist-info → scrapling-0.3.1.dist-info}/licenses/LICENSE +0 -0
scrapling/fetchers.py
CHANGED
@@ -1,289 +1,135 @@
|
|
1
|
-
from scrapling.core._types import (
|
2
|
-
|
3
|
-
|
4
|
-
|
1
|
+
from scrapling.core._types import (
|
2
|
+
Callable,
|
3
|
+
Dict,
|
4
|
+
List,
|
5
|
+
Optional,
|
6
|
+
SelectorWaitStates,
|
7
|
+
Iterable,
|
8
|
+
)
|
9
|
+
from scrapling.engines import (
|
10
|
+
FetcherSession,
|
11
|
+
StealthySession,
|
12
|
+
AsyncStealthySession,
|
13
|
+
DynamicSession,
|
14
|
+
AsyncDynamicSession,
|
15
|
+
FetcherClient as _FetcherClient,
|
16
|
+
AsyncFetcherClient as _AsyncFetcherClient,
|
17
|
+
)
|
5
18
|
from scrapling.engines.toolbelt import BaseFetcher, Response
|
6
19
|
|
20
|
+
__FetcherClientInstance__ = _FetcherClient()
|
21
|
+
__AsyncFetcherClientInstance__ = _AsyncFetcherClient()
|
7
22
|
|
8
|
-
class Fetcher(BaseFetcher):
|
9
|
-
"""A basic `Fetcher` class type that can only do basic GET, POST, PUT, and DELETE HTTP requests based on httpx.
|
10
|
-
|
11
|
-
Any additional keyword arguments passed to the methods below are passed to the respective httpx's method directly.
|
12
|
-
"""
|
13
|
-
@classmethod
|
14
|
-
def get(
|
15
|
-
cls, url: str, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = 10, stealthy_headers: bool = True,
|
16
|
-
proxy: Optional[str] = None, retries: Optional[int] = 3, custom_config: Dict = None, **kwargs: Dict) -> Response:
|
17
|
-
"""Make basic HTTP GET request for you but with some added flavors.
|
18
|
-
|
19
|
-
:param url: Target url.
|
20
|
-
:param follow_redirects: As the name says -- if enabled (default), redirects will be followed.
|
21
|
-
:param timeout: The time to wait for the request to finish in seconds. The default is 10 seconds.
|
22
|
-
:param stealthy_headers: If enabled (default), Fetcher will create and add real browser's headers and
|
23
|
-
create a referer header as if this request had came from Google's search of this URL's domain.
|
24
|
-
:param proxy: A string of a proxy to use for http and https requests, the format accepted is `http://username:password@localhost:8030`
|
25
|
-
:param retries: The number of retries to do through httpx if the request failed for any reason. The default is 3 retries.
|
26
|
-
:param custom_config: A dictionary of custom parser arguments to use with this request. Any argument passed will override any class parameters values.
|
27
|
-
:param kwargs: Any additional keyword arguments are passed directly to `httpx.get()` function so check httpx documentation for details.
|
28
|
-
:return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers`
|
29
|
-
"""
|
30
|
-
if not custom_config:
|
31
|
-
custom_config = {}
|
32
|
-
elif not isinstance(custom_config, dict):
|
33
|
-
ValueError(f"The custom parser config must be of type dictionary, got {cls.__class__}")
|
34
|
-
|
35
|
-
adaptor_arguments = tuple({**cls._generate_parser_arguments(), **custom_config}.items())
|
36
|
-
response_object = StaticEngine(url, proxy, stealthy_headers, follow_redirects, timeout, retries, adaptor_arguments=adaptor_arguments).get(**kwargs)
|
37
|
-
return response_object
|
38
|
-
|
39
|
-
@classmethod
|
40
|
-
def post(
|
41
|
-
cls, url: str, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = 10, stealthy_headers: bool = True,
|
42
|
-
proxy: Optional[str] = None, retries: Optional[int] = 3, custom_config: Dict = None, **kwargs: Dict) -> Response:
|
43
|
-
"""Make basic HTTP POST request for you but with some added flavors.
|
44
|
-
|
45
|
-
:param url: Target url.
|
46
|
-
:param follow_redirects: As the name says -- if enabled (default), redirects will be followed.
|
47
|
-
:param timeout: The time to wait for the request to finish in seconds. The default is 10 seconds.
|
48
|
-
:param stealthy_headers: If enabled (default), Fetcher will create and add real browser's headers and
|
49
|
-
create a referer header as if this request came from Google's search of this URL's domain.
|
50
|
-
:param proxy: A string of a proxy to use for http and https requests, the format accepted is `http://username:password@localhost:8030`
|
51
|
-
:param retries: The number of retries to do through httpx if the request failed for any reason. The default is 3 retries.
|
52
|
-
:param custom_config: A dictionary of custom parser arguments to use with this request. Any argument passed will override any class parameters values.
|
53
|
-
:param kwargs: Any additional keyword arguments are passed directly to `httpx.post()` function so check httpx documentation for details.
|
54
|
-
:return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers`
|
55
|
-
"""
|
56
|
-
if not custom_config:
|
57
|
-
custom_config = {}
|
58
|
-
elif not isinstance(custom_config, dict):
|
59
|
-
ValueError(f"The custom parser config must be of type dictionary, got {cls.__class__}")
|
60
|
-
|
61
|
-
adaptor_arguments = tuple({**cls._generate_parser_arguments(), **custom_config}.items())
|
62
|
-
response_object = StaticEngine(url, proxy, stealthy_headers, follow_redirects, timeout, retries, adaptor_arguments=adaptor_arguments).post(**kwargs)
|
63
|
-
return response_object
|
64
|
-
|
65
|
-
@classmethod
|
66
|
-
def put(
|
67
|
-
cls, url: str, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = 10, stealthy_headers: bool = True,
|
68
|
-
proxy: Optional[str] = None, retries: Optional[int] = 3, custom_config: Dict = None, **kwargs: Dict) -> Response:
|
69
|
-
"""Make basic HTTP PUT request for you but with some added flavors.
|
70
23
|
|
71
|
-
|
72
|
-
|
73
|
-
:param timeout: The time to wait for the request to finish in seconds. The default is 10 seconds.
|
74
|
-
:param stealthy_headers: If enabled (default), Fetcher will create and add real browser's headers and
|
75
|
-
create a referer header as if this request came from Google's search of this URL's domain.
|
76
|
-
:param proxy: A string of a proxy to use for http and https requests, the format accepted is `http://username:password@localhost:8030`
|
77
|
-
:param retries: The number of retries to do through httpx if the request failed for any reason. The default is 3 retries.
|
78
|
-
:param custom_config: A dictionary of custom parser arguments to use with this request. Any argument passed will override any class parameters values.
|
79
|
-
:param kwargs: Any additional keyword arguments are passed directly to `httpx.put()` function so check httpx documentation for details.
|
80
|
-
|
81
|
-
:return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers`
|
82
|
-
"""
|
83
|
-
if not custom_config:
|
84
|
-
custom_config = {}
|
85
|
-
elif not isinstance(custom_config, dict):
|
86
|
-
ValueError(f"The custom parser config must be of type dictionary, got {cls.__class__}")
|
87
|
-
|
88
|
-
adaptor_arguments = tuple({**cls._generate_parser_arguments(), **custom_config}.items())
|
89
|
-
response_object = StaticEngine(url, proxy, stealthy_headers, follow_redirects, timeout, retries, adaptor_arguments=adaptor_arguments).put(**kwargs)
|
90
|
-
return response_object
|
91
|
-
|
92
|
-
@classmethod
|
93
|
-
def delete(
|
94
|
-
cls, url: str, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = 10, stealthy_headers: bool = True,
|
95
|
-
proxy: Optional[str] = None, retries: Optional[int] = 3, custom_config: Dict = None, **kwargs: Dict) -> Response:
|
96
|
-
"""Make basic HTTP DELETE request for you but with some added flavors.
|
97
|
-
|
98
|
-
:param url: Target url
|
99
|
-
:param follow_redirects: As the name says -- if enabled (default), redirects will be followed.
|
100
|
-
:param timeout: The time to wait for the request to finish in seconds. The default is 10 seconds.
|
101
|
-
:param stealthy_headers: If enabled (default), Fetcher will create and add real browser's headers and
|
102
|
-
create a referer header as if this request came from Google's search of this URL's domain.
|
103
|
-
:param proxy: A string of a proxy to use for http and https requests, the format accepted is `http://username:password@localhost:8030`
|
104
|
-
:param retries: The number of retries to do through httpx if the request failed for any reason. The default is 3 retries.
|
105
|
-
:param custom_config: A dictionary of custom parser arguments to use with this request. Any argument passed will override any class parameters values.
|
106
|
-
:param kwargs: Any additional keyword arguments are passed directly to `httpx.delete()` function so check httpx documentation for details.
|
107
|
-
:return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers`
|
108
|
-
"""
|
109
|
-
if not custom_config:
|
110
|
-
custom_config = {}
|
111
|
-
elif not isinstance(custom_config, dict):
|
112
|
-
ValueError(f"The custom parser config must be of type dictionary, got {cls.__class__}")
|
113
|
-
|
114
|
-
adaptor_arguments = tuple({**cls._generate_parser_arguments(), **custom_config}.items())
|
115
|
-
response_object = StaticEngine(url, proxy, stealthy_headers, follow_redirects, timeout, retries, adaptor_arguments=adaptor_arguments).delete(**kwargs)
|
116
|
-
return response_object
|
117
|
-
|
118
|
-
|
119
|
-
class AsyncFetcher(Fetcher):
|
120
|
-
@classmethod
|
121
|
-
async def get(
|
122
|
-
cls, url: str, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = 10, stealthy_headers: bool = True,
|
123
|
-
proxy: Optional[str] = None, retries: Optional[int] = 3, custom_config: Dict = None, **kwargs: Dict) -> Response:
|
124
|
-
"""Make basic HTTP GET request for you but with some added flavors.
|
125
|
-
|
126
|
-
:param url: Target url.
|
127
|
-
:param follow_redirects: As the name says -- if enabled (default), redirects will be followed.
|
128
|
-
:param timeout: The time to wait for the request to finish in seconds. The default is 10 seconds.
|
129
|
-
:param stealthy_headers: If enabled (default), Fetcher will create and add real browser's headers and
|
130
|
-
create a referer header as if this request had came from Google's search of this URL's domain.
|
131
|
-
:param proxy: A string of a proxy to use for http and https requests, the format accepted is `http://username:password@localhost:8030`
|
132
|
-
:param retries: The number of retries to do through httpx if the request failed for any reason. The default is 3 retries.
|
133
|
-
:param custom_config: A dictionary of custom parser arguments to use with this request. Any argument passed will override any class parameters values.
|
134
|
-
:param kwargs: Any additional keyword arguments are passed directly to `httpx.get()` function so check httpx documentation for details.
|
135
|
-
:return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers`
|
136
|
-
"""
|
137
|
-
if not custom_config:
|
138
|
-
custom_config = {}
|
139
|
-
elif not isinstance(custom_config, dict):
|
140
|
-
ValueError(f"The custom parser config must be of type dictionary, got {cls.__class__}")
|
141
|
-
|
142
|
-
adaptor_arguments = tuple({**cls._generate_parser_arguments(), **custom_config}.items())
|
143
|
-
response_object = await StaticEngine(url, proxy, stealthy_headers, follow_redirects, timeout, retries=retries, adaptor_arguments=adaptor_arguments).async_get(**kwargs)
|
144
|
-
return response_object
|
145
|
-
|
146
|
-
@classmethod
|
147
|
-
async def post(
|
148
|
-
cls, url: str, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = 10, stealthy_headers: bool = True,
|
149
|
-
proxy: Optional[str] = None, retries: Optional[int] = 3, custom_config: Dict = None, **kwargs: Dict) -> Response:
|
150
|
-
"""Make basic HTTP POST request for you but with some added flavors.
|
151
|
-
|
152
|
-
:param url: Target url.
|
153
|
-
:param follow_redirects: As the name says -- if enabled (default), redirects will be followed.
|
154
|
-
:param timeout: The time to wait for the request to finish in seconds. The default is 10 seconds.
|
155
|
-
:param stealthy_headers: If enabled (default), Fetcher will create and add real browser's headers and
|
156
|
-
create a referer header as if this request came from Google's search of this URL's domain.
|
157
|
-
:param proxy: A string of a proxy to use for http and https requests, the format accepted is `http://username:password@localhost:8030`
|
158
|
-
:param retries: The number of retries to do through httpx if the request failed for any reason. The default is 3 retries.
|
159
|
-
:param custom_config: A dictionary of custom parser arguments to use with this request. Any argument passed will override any class parameters values.
|
160
|
-
:param kwargs: Any additional keyword arguments are passed directly to `httpx.post()` function so check httpx documentation for details.
|
161
|
-
:return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers`
|
162
|
-
"""
|
163
|
-
if not custom_config:
|
164
|
-
custom_config = {}
|
165
|
-
elif not isinstance(custom_config, dict):
|
166
|
-
ValueError(f"The custom parser config must be of type dictionary, got {cls.__class__}")
|
167
|
-
|
168
|
-
adaptor_arguments = tuple({**cls._generate_parser_arguments(), **custom_config}.items())
|
169
|
-
response_object = await StaticEngine(url, proxy, stealthy_headers, follow_redirects, timeout, retries=retries, adaptor_arguments=adaptor_arguments).async_post(**kwargs)
|
170
|
-
return response_object
|
171
|
-
|
172
|
-
@classmethod
|
173
|
-
async def put(
|
174
|
-
cls, url: str, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = 10, stealthy_headers: bool = True,
|
175
|
-
proxy: Optional[str] = None, retries: Optional[int] = 3, custom_config: Dict = None, **kwargs: Dict) -> Response:
|
176
|
-
"""Make basic HTTP PUT request for you but with some added flavors.
|
177
|
-
|
178
|
-
:param url: Target url
|
179
|
-
:param follow_redirects: As the name says -- if enabled (default), redirects will be followed.
|
180
|
-
:param timeout: The time to wait for the request to finish in seconds. The default is 10 seconds.
|
181
|
-
:param stealthy_headers: If enabled (default), Fetcher will create and add real browser's headers and
|
182
|
-
create a referer header as if this request came from Google's search of this URL's domain.
|
183
|
-
:param proxy: A string of a proxy to use for http and https requests, the format accepted is `http://username:password@localhost:8030`
|
184
|
-
:param retries: The number of retries to do through httpx if the request failed for any reason. The default is 3 retries.
|
185
|
-
:param custom_config: A dictionary of custom parser arguments to use with this request. Any argument passed will override any class parameters values.
|
186
|
-
:param kwargs: Any additional keyword arguments are passed directly to `httpx.put()` function so check httpx documentation for details.
|
187
|
-
:return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers`
|
188
|
-
"""
|
189
|
-
if not custom_config:
|
190
|
-
custom_config = {}
|
191
|
-
elif not isinstance(custom_config, dict):
|
192
|
-
ValueError(f"The custom parser config must be of type dictionary, got {cls.__class__}")
|
24
|
+
class Fetcher(BaseFetcher):
|
25
|
+
"""A basic `Fetcher` class type that can only do basic GET, POST, PUT, and DELETE HTTP requests based on `curl_cffi`."""
|
193
26
|
|
194
|
-
|
195
|
-
|
196
|
-
|
27
|
+
get = __FetcherClientInstance__.get
|
28
|
+
post = __FetcherClientInstance__.post
|
29
|
+
put = __FetcherClientInstance__.put
|
30
|
+
delete = __FetcherClientInstance__.delete
|
197
31
|
|
198
|
-
@classmethod
|
199
|
-
async def delete(
|
200
|
-
cls, url: str, follow_redirects: bool = True, timeout: Optional[Union[int, float]] = 10, stealthy_headers: bool = True,
|
201
|
-
proxy: Optional[str] = None, retries: Optional[int] = 3, custom_config: Dict = None, **kwargs: Dict) -> Response:
|
202
|
-
"""Make basic HTTP DELETE request for you but with some added flavors.
|
203
32
|
|
204
|
-
|
205
|
-
|
206
|
-
:param timeout: The time to wait for the request to finish in seconds. The default is 10 seconds.
|
207
|
-
:param stealthy_headers: If enabled (default), Fetcher will create and add real browser's headers and
|
208
|
-
create a referer header as if this request came from Google's search of this URL's domain.
|
209
|
-
:param proxy: A string of a proxy to use for http and https requests, the format accepted is `http://username:password@localhost:8030`
|
210
|
-
:param retries: The number of retries to do through httpx if the request failed for any reason. The default is 3 retries.
|
211
|
-
:param custom_config: A dictionary of custom parser arguments to use with this request. Any argument passed will override any class parameters values.
|
212
|
-
:param kwargs: Any additional keyword arguments are passed directly to `httpx.delete()` function so check httpx documentation for details.
|
213
|
-
:return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers`
|
214
|
-
"""
|
215
|
-
if not custom_config:
|
216
|
-
custom_config = {}
|
217
|
-
elif not isinstance(custom_config, dict):
|
218
|
-
ValueError(f"The custom parser config must be of type dictionary, got {cls.__class__}")
|
33
|
+
class AsyncFetcher(BaseFetcher):
|
34
|
+
"""A basic `Fetcher` class type that can only do basic GET, POST, PUT, and DELETE HTTP requests based on `curl_cffi`."""
|
219
35
|
|
220
|
-
|
221
|
-
|
222
|
-
|
36
|
+
get = __AsyncFetcherClientInstance__.get
|
37
|
+
post = __AsyncFetcherClientInstance__.post
|
38
|
+
put = __AsyncFetcherClientInstance__.put
|
39
|
+
delete = __AsyncFetcherClientInstance__.delete
|
223
40
|
|
224
41
|
|
225
42
|
class StealthyFetcher(BaseFetcher):
|
226
|
-
"""A `Fetcher` class type that is completely stealthy fetcher that uses a modified version of Firefox.
|
43
|
+
"""A `Fetcher` class type that is a completely stealthy fetcher that uses a modified version of Firefox.
|
227
44
|
|
228
|
-
|
229
|
-
|
45
|
+
It works as real browsers passing almost all online tests/protections based on Camoufox.
|
46
|
+
Other added flavors include setting the faked OS fingerprints to match the user's OS, and the referer of every request is set as if this request came from Google's search of this URL's domain.
|
230
47
|
"""
|
48
|
+
|
231
49
|
@classmethod
|
232
50
|
def fetch(
|
233
|
-
|
234
|
-
|
235
|
-
|
236
|
-
|
237
|
-
|
238
|
-
|
51
|
+
cls,
|
52
|
+
url: str,
|
53
|
+
headless: bool = True, # noqa: F821
|
54
|
+
block_images: bool = False,
|
55
|
+
disable_resources: bool = False,
|
56
|
+
block_webrtc: bool = False,
|
57
|
+
allow_webgl: bool = True,
|
58
|
+
network_idle: bool = False,
|
59
|
+
humanize: bool | float = True,
|
60
|
+
solve_cloudflare: bool = False,
|
61
|
+
wait: int | float = 0,
|
62
|
+
timeout: int | float = 30000,
|
63
|
+
page_action: Optional[Callable] = None,
|
64
|
+
wait_selector: Optional[str] = None,
|
65
|
+
init_script: Optional[str] = None,
|
66
|
+
addons: Optional[List[str]] = None,
|
67
|
+
wait_selector_state: SelectorWaitStates = "attached",
|
68
|
+
cookies: Optional[List[Dict]] = None,
|
69
|
+
google_search: bool = True,
|
70
|
+
extra_headers: Optional[Dict[str, str]] = None,
|
71
|
+
proxy: Optional[str | Dict[str, str]] = None,
|
72
|
+
os_randomize: bool = False,
|
73
|
+
disable_ads: bool = False,
|
74
|
+
geoip: bool = False,
|
75
|
+
custom_config: Optional[Dict] = None,
|
76
|
+
additional_args: Optional[Dict] = None,
|
239
77
|
) -> Response:
|
240
78
|
"""
|
241
79
|
Opens up a browser and do your request based on your chosen options below.
|
242
80
|
|
243
81
|
:param url: Target url.
|
244
|
-
:param headless: Run the browser in headless/hidden (default),
|
82
|
+
:param headless: Run the browser in headless/hidden (default), or headful/visible mode.
|
245
83
|
:param block_images: Prevent the loading of images through Firefox preferences.
|
246
84
|
This can help save your proxy usage but be careful with this option as it makes some websites never finish loading.
|
247
|
-
:param disable_resources: Drop requests of unnecessary resources for a speed boost. It depends but it made requests ~25% faster in my tests for some websites.
|
85
|
+
:param disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites.
|
248
86
|
Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`.
|
249
87
|
This can help save your proxy usage but be careful with this option as it makes some websites never finish loading.
|
250
88
|
:param block_webrtc: Blocks WebRTC entirely.
|
89
|
+
:param cookies: Set cookies for the next request.
|
251
90
|
:param addons: List of Firefox addons to use. Must be paths to extracted addons.
|
252
|
-
:param disable_ads: Disabled by default, this installs `uBlock Origin` addon on the browser if enabled.
|
253
91
|
:param humanize: Humanize the cursor movement. Takes either True or the MAX duration in seconds of the cursor movement. The cursor typically takes up to 1.5 seconds to move across the window.
|
254
|
-
:param
|
255
|
-
:param
|
256
|
-
It will also calculate and spoof the browser's language based on the distribution of language speakers in the target region.
|
92
|
+
:param solve_cloudflare: Solves all 3 types of the Cloudflare's Turnstile wait page before returning the response to you.
|
93
|
+
:param allow_webgl: Enabled by default. Disabling WebGL is not recommended as many WAFs now check if WebGL is enabled.
|
257
94
|
:param network_idle: Wait for the page until there are no network connections for at least 500 ms.
|
95
|
+
:param disable_ads: Disabled by default, this installs the `uBlock Origin` addon on the browser if enabled.
|
258
96
|
:param os_randomize: If enabled, Scrapling will randomize the OS fingerprints used. The default is Scrapling matching the fingerprints with the current OS.
|
259
|
-
:param
|
260
|
-
:param
|
97
|
+
:param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object.
|
98
|
+
:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000
|
261
99
|
:param page_action: Added for automation. A function that takes the `page` object, does the automation you need, then returns `page` again.
|
262
|
-
:param wait_selector: Wait for a specific
|
263
|
-
:param
|
264
|
-
:param
|
100
|
+
:param wait_selector: Wait for a specific CSS selector to be in a specific state.
|
101
|
+
:param init_script: An absolute path to a JavaScript file to be executed on page creation with this request.
|
102
|
+
:param geoip: Recommended to use with proxies; Automatically use IP's longitude, latitude, timezone, country, locale, and spoof the WebRTC IP address.
|
103
|
+
It will also calculate and spoof the browser's language based on the distribution of language speakers in the target region.
|
104
|
+
:param wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
|
105
|
+
:param google_search: Enabled by default, Scrapling will set the referer header to be as if this request came from a Google search of this website's domain name.
|
265
106
|
:param extra_headers: A dictionary of extra headers to add to the request. _The referer set by the `google_search` argument takes priority over the referer set here if used together._
|
266
107
|
:param proxy: The proxy to be used with requests, it can be a string or a dictionary with the keys 'server', 'username', and 'password' only.
|
267
108
|
:param custom_config: A dictionary of custom parser arguments to use with this request. Any argument passed will override any class parameters values.
|
268
|
-
:param
|
269
|
-
:return: A `Response` object
|
109
|
+
:param additional_args: Additional arguments to be passed to Camoufox as additional settings, and it takes higher priority than Scrapling's settings.
|
110
|
+
:return: A `Response` object.
|
270
111
|
"""
|
271
112
|
if not custom_config:
|
272
113
|
custom_config = {}
|
273
114
|
elif not isinstance(custom_config, dict):
|
274
|
-
ValueError(
|
115
|
+
ValueError(
|
116
|
+
f"The custom parser config must be of type dictionary, got {cls.__class__}"
|
117
|
+
)
|
275
118
|
|
276
|
-
|
119
|
+
with StealthySession(
|
277
120
|
wait=wait,
|
121
|
+
max_pages=1,
|
278
122
|
proxy=proxy,
|
279
123
|
geoip=geoip,
|
280
124
|
addons=addons,
|
281
125
|
timeout=timeout,
|
126
|
+
cookies=cookies,
|
282
127
|
headless=headless,
|
283
128
|
humanize=humanize,
|
284
129
|
disable_ads=disable_ads,
|
285
130
|
allow_webgl=allow_webgl,
|
286
131
|
page_action=page_action,
|
132
|
+
init_script=init_script,
|
287
133
|
network_idle=network_idle,
|
288
134
|
block_images=block_images,
|
289
135
|
block_webrtc=block_webrtc,
|
@@ -291,69 +137,98 @@ class StealthyFetcher(BaseFetcher):
|
|
291
137
|
wait_selector=wait_selector,
|
292
138
|
google_search=google_search,
|
293
139
|
extra_headers=extra_headers,
|
140
|
+
solve_cloudflare=solve_cloudflare,
|
294
141
|
disable_resources=disable_resources,
|
295
142
|
wait_selector_state=wait_selector_state,
|
296
|
-
|
297
|
-
|
298
|
-
)
|
299
|
-
|
143
|
+
selector_config={**cls._generate_parser_arguments(), **custom_config},
|
144
|
+
additional_args=additional_args or {},
|
145
|
+
) as engine:
|
146
|
+
return engine.fetch(url)
|
300
147
|
|
301
148
|
@classmethod
|
302
149
|
async def async_fetch(
|
303
|
-
|
304
|
-
|
305
|
-
|
306
|
-
|
307
|
-
|
308
|
-
|
150
|
+
cls,
|
151
|
+
url: str,
|
152
|
+
headless: bool = True, # noqa: F821
|
153
|
+
block_images: bool = False,
|
154
|
+
disable_resources: bool = False,
|
155
|
+
block_webrtc: bool = False,
|
156
|
+
allow_webgl: bool = True,
|
157
|
+
network_idle: bool = False,
|
158
|
+
humanize: bool | float = True,
|
159
|
+
solve_cloudflare: bool = False,
|
160
|
+
wait: int | float = 0,
|
161
|
+
timeout: int | float = 30000,
|
162
|
+
page_action: Optional[Callable] = None,
|
163
|
+
wait_selector: Optional[str] = None,
|
164
|
+
init_script: Optional[str] = None,
|
165
|
+
addons: Optional[List[str]] = None,
|
166
|
+
wait_selector_state: SelectorWaitStates = "attached",
|
167
|
+
cookies: Optional[List[Dict]] = None,
|
168
|
+
google_search: bool = True,
|
169
|
+
extra_headers: Optional[Dict[str, str]] = None,
|
170
|
+
proxy: Optional[str | Dict[str, str]] = None,
|
171
|
+
os_randomize: bool = False,
|
172
|
+
disable_ads: bool = False,
|
173
|
+
geoip: bool = False,
|
174
|
+
custom_config: Optional[Dict] = None,
|
175
|
+
additional_args: Optional[Dict] = None,
|
309
176
|
) -> Response:
|
310
177
|
"""
|
311
178
|
Opens up a browser and do your request based on your chosen options below.
|
312
179
|
|
313
180
|
:param url: Target url.
|
314
|
-
:param headless: Run the browser in headless/hidden (default),
|
181
|
+
:param headless: Run the browser in headless/hidden (default), or headful/visible mode.
|
315
182
|
:param block_images: Prevent the loading of images through Firefox preferences.
|
316
183
|
This can help save your proxy usage but be careful with this option as it makes some websites never finish loading.
|
317
|
-
:param disable_resources: Drop requests of unnecessary resources for a speed boost. It depends but it made requests ~25% faster in my tests for some websites.
|
184
|
+
:param disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites.
|
318
185
|
Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`.
|
319
186
|
This can help save your proxy usage but be careful with this option as it makes some websites never finish loading.
|
320
187
|
:param block_webrtc: Blocks WebRTC entirely.
|
188
|
+
:param cookies: Set cookies for the next request.
|
321
189
|
:param addons: List of Firefox addons to use. Must be paths to extracted addons.
|
322
|
-
:param disable_ads: Disabled by default, this installs `uBlock Origin` addon on the browser if enabled.
|
323
190
|
:param humanize: Humanize the cursor movement. Takes either True or the MAX duration in seconds of the cursor movement. The cursor typically takes up to 1.5 seconds to move across the window.
|
324
|
-
:param
|
325
|
-
:param
|
326
|
-
It will also calculate and spoof the browser's language based on the distribution of language speakers in the target region.
|
191
|
+
:param solve_cloudflare: Solves all 3 types of the Cloudflare's Turnstile wait page before returning the response to you.
|
192
|
+
:param allow_webgl: Enabled by default. Disabling WebGL is not recommended as many WAFs now check if WebGL is enabled.
|
327
193
|
:param network_idle: Wait for the page until there are no network connections for at least 500 ms.
|
194
|
+
:param disable_ads: Disabled by default, this installs the `uBlock Origin` addon on the browser if enabled.
|
328
195
|
:param os_randomize: If enabled, Scrapling will randomize the OS fingerprints used. The default is Scrapling matching the fingerprints with the current OS.
|
329
|
-
:param
|
330
|
-
:param
|
196
|
+
:param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object.
|
197
|
+
:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000
|
331
198
|
:param page_action: Added for automation. A function that takes the `page` object, does the automation you need, then returns `page` again.
|
332
|
-
:param wait_selector: Wait for a specific
|
333
|
-
:param
|
334
|
-
:param
|
199
|
+
:param wait_selector: Wait for a specific CSS selector to be in a specific state.
|
200
|
+
:param init_script: An absolute path to a JavaScript file to be executed on page creation with this request.
|
201
|
+
:param geoip: Recommended to use with proxies; Automatically use IP's longitude, latitude, timezone, country, locale, and spoof the WebRTC IP address.
|
202
|
+
It will also calculate and spoof the browser's language based on the distribution of language speakers in the target region.
|
203
|
+
:param wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
|
204
|
+
:param google_search: Enabled by default, Scrapling will set the referer header to be as if this request came from a Google search of this website's domain name.
|
335
205
|
:param extra_headers: A dictionary of extra headers to add to the request. _The referer set by the `google_search` argument takes priority over the referer set here if used together._
|
336
206
|
:param proxy: The proxy to be used with requests, it can be a string or a dictionary with the keys 'server', 'username', and 'password' only.
|
337
207
|
:param custom_config: A dictionary of custom parser arguments to use with this request. Any argument passed will override any class parameters values.
|
338
|
-
:param
|
339
|
-
:return: A `Response` object
|
208
|
+
:param additional_args: Additional arguments to be passed to Camoufox as additional settings, and it takes higher priority than Scrapling's settings.
|
209
|
+
:return: A `Response` object.
|
340
210
|
"""
|
341
211
|
if not custom_config:
|
342
212
|
custom_config = {}
|
343
213
|
elif not isinstance(custom_config, dict):
|
344
|
-
ValueError(
|
214
|
+
ValueError(
|
215
|
+
f"The custom parser config must be of type dictionary, got {cls.__class__}"
|
216
|
+
)
|
345
217
|
|
346
|
-
|
218
|
+
async with AsyncStealthySession(
|
347
219
|
wait=wait,
|
220
|
+
max_pages=1,
|
348
221
|
proxy=proxy,
|
349
222
|
geoip=geoip,
|
350
223
|
addons=addons,
|
351
224
|
timeout=timeout,
|
225
|
+
cookies=cookies,
|
352
226
|
headless=headless,
|
353
227
|
humanize=humanize,
|
354
228
|
disable_ads=disable_ads,
|
355
229
|
allow_webgl=allow_webgl,
|
356
230
|
page_action=page_action,
|
231
|
+
init_script=init_script,
|
357
232
|
network_idle=network_idle,
|
358
233
|
block_images=block_images,
|
359
234
|
block_webrtc=block_webrtc,
|
@@ -361,173 +236,204 @@ class StealthyFetcher(BaseFetcher):
|
|
361
236
|
wait_selector=wait_selector,
|
362
237
|
google_search=google_search,
|
363
238
|
extra_headers=extra_headers,
|
239
|
+
solve_cloudflare=solve_cloudflare,
|
364
240
|
disable_resources=disable_resources,
|
365
241
|
wait_selector_state=wait_selector_state,
|
366
|
-
|
367
|
-
|
368
|
-
)
|
369
|
-
|
242
|
+
selector_config={**cls._generate_parser_arguments(), **custom_config},
|
243
|
+
additional_args=additional_args or {},
|
244
|
+
) as engine:
|
245
|
+
return await engine.fetch(url)
|
370
246
|
|
371
247
|
|
372
|
-
class
|
248
|
+
class DynamicFetcher(BaseFetcher):
|
373
249
|
"""A `Fetcher` class type that provide many options, all of them are based on PlayWright.
|
374
250
|
|
375
251
|
Using this Fetcher class, you can do requests with:
|
376
252
|
- Vanilla Playwright without any modifications other than the ones you chose.
|
377
|
-
- Stealthy Playwright with the stealth mode I wrote for it. It's still a work in progress but it bypasses many online tests like bot.sannysoft.com
|
253
|
+
- Stealthy Playwright with the stealth mode I wrote for it. It's still a work in progress, but it bypasses many online tests like bot.sannysoft.com
|
378
254
|
Some of the things stealth mode does include:
|
379
255
|
1) Patches the CDP runtime fingerprint.
|
380
256
|
2) Mimics some of the real browsers' properties by injecting several JS files and using custom options.
|
381
257
|
3) Using custom flags on launch to hide Playwright even more and make it faster.
|
382
|
-
4) Generates real browser's headers of the same type and same user OS then append it to the request.
|
383
|
-
- Real browsers by passing the `real_chrome` argument or the CDP URL of your browser to be controlled by the Fetcher and most of the options can be enabled on it.
|
258
|
+
4) Generates real browser's headers of the same type and same user OS, then append it to the request.
|
259
|
+
- Real browsers by passing the `real_chrome` argument or the CDP URL of your browser to be controlled by the Fetcher, and most of the options can be enabled on it.
|
384
260
|
- NSTBrowser's docker browserless option by passing the CDP URL and enabling `nstbrowser_mode` option.
|
385
261
|
|
386
|
-
> Note that these are the main options with PlayWright but it can be mixed
|
262
|
+
> Note that these are the main options with PlayWright, but it can be mixed.
|
387
263
|
"""
|
264
|
+
|
388
265
|
@classmethod
|
389
266
|
def fetch(
|
390
|
-
|
391
|
-
|
392
|
-
|
393
|
-
|
394
|
-
|
395
|
-
|
396
|
-
|
397
|
-
|
398
|
-
|
267
|
+
cls,
|
268
|
+
url: str,
|
269
|
+
headless: bool = True,
|
270
|
+
google_search: bool = True,
|
271
|
+
hide_canvas: bool = False,
|
272
|
+
disable_webgl: bool = False,
|
273
|
+
real_chrome: bool = False,
|
274
|
+
stealth: bool = False,
|
275
|
+
wait: int | float = 0,
|
276
|
+
page_action: Optional[Callable] = None,
|
277
|
+
proxy: Optional[str | Dict[str, str]] = None,
|
278
|
+
locale: str = "en-US",
|
279
|
+
extra_headers: Optional[Dict[str, str]] = None,
|
280
|
+
useragent: Optional[str] = None,
|
281
|
+
cdp_url: Optional[str] = None,
|
282
|
+
timeout: int | float = 30000,
|
283
|
+
disable_resources: bool = False,
|
284
|
+
wait_selector: Optional[str] = None,
|
285
|
+
init_script: Optional[str] = None,
|
286
|
+
cookies: Optional[Iterable[Dict]] = None,
|
287
|
+
network_idle: bool = False,
|
288
|
+
wait_selector_state: SelectorWaitStates = "attached",
|
289
|
+
custom_config: Optional[Dict] = None,
|
399
290
|
) -> Response:
|
400
291
|
"""Opens up a browser and do your request based on your chosen options below.
|
401
292
|
|
402
293
|
:param url: Target url.
|
403
294
|
:param headless: Run the browser in headless/hidden (default), or headful/visible mode.
|
404
|
-
:param disable_resources: Drop requests of unnecessary resources for speed boost. It depends but it made requests ~25% faster in my tests for some websites.
|
295
|
+
:param disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites.
|
405
296
|
Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`.
|
406
297
|
This can help save your proxy usage but be careful with this option as it makes some websites never finish loading.
|
407
298
|
:param useragent: Pass a useragent string to be used. Otherwise the fetcher will generate a real Useragent of the same browser and use it.
|
299
|
+
:param cookies: Set cookies for the next request.
|
408
300
|
:param network_idle: Wait for the page until there are no network connections for at least 500 ms.
|
409
|
-
:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is
|
410
|
-
:param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning `Response` object.
|
411
|
-
:param locale: Set the locale for the browser if wanted. The default value is `en-US`.
|
301
|
+
:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000
|
302
|
+
:param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object.
|
412
303
|
:param page_action: Added for automation. A function that takes the `page` object, does the automation you need, then returns `page` again.
|
413
|
-
:param wait_selector: Wait for a specific
|
414
|
-
:param
|
304
|
+
:param wait_selector: Wait for a specific CSS selector to be in a specific state.
|
305
|
+
:param init_script: An absolute path to a JavaScript file to be executed on page creation with this request.
|
306
|
+
:param locale: Set the locale for the browser if wanted. The default value is `en-US`.
|
307
|
+
:param wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
|
415
308
|
:param stealth: Enables stealth mode, check the documentation to see what stealth mode does currently.
|
416
|
-
:param real_chrome: If you have
|
309
|
+
:param real_chrome: If you have a Chrome browser installed on your device, enable this, and the Fetcher will launch an instance of your browser and use it.
|
417
310
|
:param hide_canvas: Add random noise to canvas operations to prevent fingerprinting.
|
418
311
|
:param disable_webgl: Disables WebGL and WebGL 2.0 support entirely.
|
419
|
-
:param
|
312
|
+
:param cdp_url: Instead of launching a new browser instance, connect to this CDP URL to control real browsers/NSTBrowser through CDP.
|
313
|
+
:param google_search: Enabled by default, Scrapling will set the referer header to be as if this request came from a Google search of this website's domain name.
|
420
314
|
:param extra_headers: A dictionary of extra headers to add to the request. _The referer set by the `google_search` argument takes priority over the referer set here if used together._
|
421
315
|
:param proxy: The proxy to be used with requests, it can be a string or a dictionary with the keys 'server', 'username', and 'password' only.
|
422
|
-
:param cdp_url: Instead of launching a new browser instance, connect to this CDP URL to control real browsers/NSTBrowser through CDP.
|
423
|
-
:param nstbrowser_mode: Enables NSTBrowser mode, it have to be used with `cdp_url` argument or it will get completely ignored.
|
424
|
-
:param nstbrowser_config: The config you want to send with requests to the NSTBrowser. If left empty, Scrapling defaults to an optimized NSTBrowser's docker browserless config.
|
425
316
|
:param custom_config: A dictionary of custom parser arguments to use with this request. Any argument passed will override any class parameters values.
|
426
|
-
:return: A `Response` object
|
317
|
+
:return: A `Response` object.
|
427
318
|
"""
|
428
319
|
if not custom_config:
|
429
320
|
custom_config = {}
|
430
321
|
elif not isinstance(custom_config, dict):
|
431
|
-
ValueError(
|
322
|
+
raise ValueError(
|
323
|
+
f"The custom parser config must be of type dictionary, got {cls.__class__}"
|
324
|
+
)
|
432
325
|
|
433
|
-
|
326
|
+
with DynamicSession(
|
434
327
|
wait=wait,
|
435
328
|
proxy=proxy,
|
436
329
|
locale=locale,
|
437
330
|
timeout=timeout,
|
438
331
|
stealth=stealth,
|
439
332
|
cdp_url=cdp_url,
|
333
|
+
cookies=cookies,
|
440
334
|
headless=headless,
|
441
335
|
useragent=useragent,
|
442
336
|
real_chrome=real_chrome,
|
443
337
|
page_action=page_action,
|
444
338
|
hide_canvas=hide_canvas,
|
339
|
+
init_script=init_script,
|
445
340
|
network_idle=network_idle,
|
446
341
|
google_search=google_search,
|
447
342
|
extra_headers=extra_headers,
|
448
343
|
wait_selector=wait_selector,
|
449
344
|
disable_webgl=disable_webgl,
|
450
|
-
nstbrowser_mode=nstbrowser_mode,
|
451
|
-
nstbrowser_config=nstbrowser_config,
|
452
345
|
disable_resources=disable_resources,
|
453
346
|
wait_selector_state=wait_selector_state,
|
454
|
-
|
455
|
-
)
|
456
|
-
|
347
|
+
selector_config={**cls._generate_parser_arguments(), **custom_config},
|
348
|
+
) as session:
|
349
|
+
return session.fetch(url)
|
457
350
|
|
458
351
|
@classmethod
|
459
352
|
async def async_fetch(
|
460
|
-
|
461
|
-
|
462
|
-
|
463
|
-
|
464
|
-
|
465
|
-
|
466
|
-
|
467
|
-
|
468
|
-
|
353
|
+
cls,
|
354
|
+
url: str,
|
355
|
+
headless: bool = True,
|
356
|
+
google_search: bool = True,
|
357
|
+
hide_canvas: bool = False,
|
358
|
+
disable_webgl: bool = False,
|
359
|
+
real_chrome: bool = False,
|
360
|
+
stealth: bool = False,
|
361
|
+
wait: int | float = 0,
|
362
|
+
page_action: Optional[Callable] = None,
|
363
|
+
proxy: Optional[str | Dict[str, str]] = None,
|
364
|
+
locale: str = "en-US",
|
365
|
+
extra_headers: Optional[Dict[str, str]] = None,
|
366
|
+
useragent: Optional[str] = None,
|
367
|
+
cdp_url: Optional[str] = None,
|
368
|
+
timeout: int | float = 30000,
|
369
|
+
disable_resources: bool = False,
|
370
|
+
wait_selector: Optional[str] = None,
|
371
|
+
init_script: Optional[str] = None,
|
372
|
+
cookies: Optional[Iterable[Dict]] = None,
|
373
|
+
network_idle: bool = False,
|
374
|
+
wait_selector_state: SelectorWaitStates = "attached",
|
375
|
+
custom_config: Optional[Dict] = None,
|
469
376
|
) -> Response:
|
470
377
|
"""Opens up a browser and do your request based on your chosen options below.
|
471
378
|
|
472
379
|
:param url: Target url.
|
473
380
|
:param headless: Run the browser in headless/hidden (default), or headful/visible mode.
|
474
|
-
:param disable_resources: Drop requests of unnecessary resources for speed boost. It depends but it made requests ~25% faster in my tests for some websites.
|
381
|
+
:param disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites.
|
475
382
|
Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`.
|
476
383
|
This can help save your proxy usage but be careful with this option as it makes some websites never finish loading.
|
477
384
|
:param useragent: Pass a useragent string to be used. Otherwise the fetcher will generate a real Useragent of the same browser and use it.
|
385
|
+
:param cookies: Set cookies for the next request.
|
478
386
|
:param network_idle: Wait for the page until there are no network connections for at least 500 ms.
|
479
|
-
:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is
|
480
|
-
:param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning `Response` object.
|
481
|
-
:param locale: Set the locale for the browser if wanted. The default value is `en-US`.
|
387
|
+
:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000
|
388
|
+
:param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object.
|
482
389
|
:param page_action: Added for automation. A function that takes the `page` object, does the automation you need, then returns `page` again.
|
483
|
-
:param wait_selector: Wait for a specific
|
484
|
-
:param
|
390
|
+
:param wait_selector: Wait for a specific CSS selector to be in a specific state.
|
391
|
+
:param init_script: An absolute path to a JavaScript file to be executed on page creation with this request.
|
392
|
+
:param locale: Set the locale for the browser if wanted. The default value is `en-US`.
|
393
|
+
:param wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
|
485
394
|
:param stealth: Enables stealth mode, check the documentation to see what stealth mode does currently.
|
486
|
-
:param real_chrome: If you have
|
395
|
+
:param real_chrome: If you have a Chrome browser installed on your device, enable this, and the Fetcher will launch an instance of your browser and use it.
|
487
396
|
:param hide_canvas: Add random noise to canvas operations to prevent fingerprinting.
|
488
397
|
:param disable_webgl: Disables WebGL and WebGL 2.0 support entirely.
|
489
|
-
:param
|
398
|
+
:param cdp_url: Instead of launching a new browser instance, connect to this CDP URL to control real browsers/NSTBrowser through CDP.
|
399
|
+
:param google_search: Enabled by default, Scrapling will set the referer header to be as if this request came from a Google search of this website's domain name.
|
490
400
|
:param extra_headers: A dictionary of extra headers to add to the request. _The referer set by the `google_search` argument takes priority over the referer set here if used together._
|
491
401
|
:param proxy: The proxy to be used with requests, it can be a string or a dictionary with the keys 'server', 'username', and 'password' only.
|
492
|
-
:param cdp_url: Instead of launching a new browser instance, connect to this CDP URL to control real browsers/NSTBrowser through CDP.
|
493
|
-
:param nstbrowser_mode: Enables NSTBrowser mode, it have to be used with `cdp_url` argument or it will get completely ignored.
|
494
|
-
:param nstbrowser_config: The config you want to send with requests to the NSTBrowser. If left empty, Scrapling defaults to an optimized NSTBrowser's docker browserless config.
|
495
402
|
:param custom_config: A dictionary of custom parser arguments to use with this request. Any argument passed will override any class parameters values.
|
496
|
-
:return: A `Response` object
|
403
|
+
:return: A `Response` object.
|
497
404
|
"""
|
498
405
|
if not custom_config:
|
499
406
|
custom_config = {}
|
500
407
|
elif not isinstance(custom_config, dict):
|
501
|
-
ValueError(
|
408
|
+
raise ValueError(
|
409
|
+
f"The custom parser config must be of type dictionary, got {cls.__class__}"
|
410
|
+
)
|
502
411
|
|
503
|
-
|
412
|
+
async with AsyncDynamicSession(
|
504
413
|
wait=wait,
|
505
414
|
proxy=proxy,
|
506
415
|
locale=locale,
|
507
416
|
timeout=timeout,
|
508
417
|
stealth=stealth,
|
509
418
|
cdp_url=cdp_url,
|
419
|
+
cookies=cookies,
|
510
420
|
headless=headless,
|
511
421
|
useragent=useragent,
|
422
|
+
max_pages=1,
|
512
423
|
real_chrome=real_chrome,
|
513
424
|
page_action=page_action,
|
514
425
|
hide_canvas=hide_canvas,
|
426
|
+
init_script=init_script,
|
515
427
|
network_idle=network_idle,
|
516
428
|
google_search=google_search,
|
517
429
|
extra_headers=extra_headers,
|
518
430
|
wait_selector=wait_selector,
|
519
431
|
disable_webgl=disable_webgl,
|
520
|
-
nstbrowser_mode=nstbrowser_mode,
|
521
|
-
nstbrowser_config=nstbrowser_config,
|
522
432
|
disable_resources=disable_resources,
|
523
433
|
wait_selector_state=wait_selector_state,
|
524
|
-
|
525
|
-
)
|
526
|
-
|
434
|
+
selector_config={**cls._generate_parser_arguments(), **custom_config},
|
435
|
+
) as session:
|
436
|
+
return await session.fetch(url)
|
527
437
|
|
528
438
|
|
529
|
-
|
530
|
-
@classmethod
|
531
|
-
def fetch(cls, url: str, browser_engine, **kwargs) -> Response:
|
532
|
-
engine = check_if_engine_usable(browser_engine)(adaptor_arguments=cls._generate_parser_arguments(), **kwargs)
|
533
|
-
return engine.fetch(url)
|
439
|
+
PlayWrightFetcher = DynamicFetcher # For backward-compatibility
|