scrapling 0.2.99__py3-none-any.whl → 0.3__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 +745 -0
- scrapling/engines/_browsers/_config_tools.py +130 -0
- scrapling/engines/_browsers/_controllers.py +630 -0
- scrapling/engines/_browsers/_page.py +93 -0
- scrapling/engines/_browsers/_validators.py +150 -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 +227 -333
- scrapling/parser.py +781 -449
- scrapling-0.3.dist-info/METADATA +409 -0
- scrapling-0.3.dist-info/RECORD +41 -0
- {scrapling-0.2.99.dist-info → scrapling-0.3.dist-info}/WHEEL +1 -1
- {scrapling-0.2.99.dist-info → scrapling-0.3.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.dist-info}/entry_points.txt +0 -0
- {scrapling-0.2.99.dist-info → scrapling-0.3.dist-info}/licenses/LICENSE +0 -0
scrapling/fetchers.py
CHANGED
@@ -1,284 +1,127 @@
|
|
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
|
+
addons: Optional[List[str]] = None,
|
66
|
+
wait_selector_state: SelectorWaitStates = "attached",
|
67
|
+
cookies: Optional[List[Dict]] = None,
|
68
|
+
google_search: bool = True,
|
69
|
+
extra_headers: Optional[Dict[str, str]] = None,
|
70
|
+
proxy: Optional[str | Dict[str, str]] = None,
|
71
|
+
os_randomize: bool = False,
|
72
|
+
disable_ads: bool = False,
|
73
|
+
geoip: bool = False,
|
74
|
+
custom_config: Optional[Dict] = None,
|
75
|
+
additional_args: Optional[Dict] = None,
|
239
76
|
) -> Response:
|
240
77
|
"""
|
241
78
|
Opens up a browser and do your request based on your chosen options below.
|
242
79
|
|
243
80
|
:param url: Target url.
|
244
|
-
:param headless: Run the browser in headless/hidden (default),
|
81
|
+
:param headless: Run the browser in headless/hidden (default), or headful/visible mode.
|
245
82
|
:param block_images: Prevent the loading of images through Firefox preferences.
|
246
83
|
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.
|
84
|
+
: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
85
|
Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`.
|
249
86
|
This can help save your proxy usage but be careful with this option as it makes some websites never finish loading.
|
250
87
|
:param block_webrtc: Blocks WebRTC entirely.
|
88
|
+
:param cookies: Set cookies for the next request.
|
251
89
|
: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
90
|
: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.
|
91
|
+
:param solve_cloudflare: Solves all 3 types of the Cloudflare's Turnstile wait page before returning the response to you.
|
92
|
+
:param allow_webgl: Enabled by default. Disabling WebGL is not recommended as many WAFs now check if WebGL is enabled.
|
257
93
|
:param network_idle: Wait for the page until there are no network connections for at least 500 ms.
|
94
|
+
:param disable_ads: Disabled by default, this installs the `uBlock Origin` addon on the browser if enabled.
|
258
95
|
: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
|
96
|
+
:param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object.
|
97
|
+
:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000
|
261
98
|
: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
|
-
|
99
|
+
:param wait_selector: Wait for a specific CSS selector to be in a specific state.
|
100
|
+
:param geoip: Recommended to use with proxies; Automatically use IP's longitude, latitude, timezone, country, locale, and spoof the WebRTC IP address.
|
101
|
+
It will also calculate and spoof the browser's language based on the distribution of language speakers in the target region.
|
102
|
+
:param wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
|
103
|
+
: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
104
|
: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
105
|
: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
106
|
: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
|
107
|
+
:param additional_args: Additional arguments to be passed to Camoufox as additional settings, and it takes higher priority than Scrapling's settings.
|
108
|
+
:return: A `Response` object.
|
270
109
|
"""
|
271
110
|
if not custom_config:
|
272
111
|
custom_config = {}
|
273
112
|
elif not isinstance(custom_config, dict):
|
274
|
-
ValueError(
|
113
|
+
ValueError(
|
114
|
+
f"The custom parser config must be of type dictionary, got {cls.__class__}"
|
115
|
+
)
|
275
116
|
|
276
|
-
|
117
|
+
with StealthySession(
|
277
118
|
wait=wait,
|
119
|
+
max_pages=1,
|
278
120
|
proxy=proxy,
|
279
121
|
geoip=geoip,
|
280
122
|
addons=addons,
|
281
123
|
timeout=timeout,
|
124
|
+
cookies=cookies,
|
282
125
|
headless=headless,
|
283
126
|
humanize=humanize,
|
284
127
|
disable_ads=disable_ads,
|
@@ -291,64 +134,90 @@ class StealthyFetcher(BaseFetcher):
|
|
291
134
|
wait_selector=wait_selector,
|
292
135
|
google_search=google_search,
|
293
136
|
extra_headers=extra_headers,
|
137
|
+
solve_cloudflare=solve_cloudflare,
|
294
138
|
disable_resources=disable_resources,
|
295
139
|
wait_selector_state=wait_selector_state,
|
296
|
-
|
297
|
-
|
298
|
-
)
|
299
|
-
|
140
|
+
selector_config={**cls._generate_parser_arguments(), **custom_config},
|
141
|
+
additional_args=additional_args or {},
|
142
|
+
) as engine:
|
143
|
+
return engine.fetch(url)
|
300
144
|
|
301
145
|
@classmethod
|
302
146
|
async def async_fetch(
|
303
|
-
|
304
|
-
|
305
|
-
|
306
|
-
|
307
|
-
|
308
|
-
|
147
|
+
cls,
|
148
|
+
url: str,
|
149
|
+
headless: bool = True, # noqa: F821
|
150
|
+
block_images: bool = False,
|
151
|
+
disable_resources: bool = False,
|
152
|
+
block_webrtc: bool = False,
|
153
|
+
allow_webgl: bool = True,
|
154
|
+
network_idle: bool = False,
|
155
|
+
humanize: bool | float = True,
|
156
|
+
solve_cloudflare: bool = False,
|
157
|
+
wait: int | float = 0,
|
158
|
+
timeout: int | float = 30000,
|
159
|
+
page_action: Optional[Callable] = None,
|
160
|
+
wait_selector: Optional[str] = None,
|
161
|
+
addons: Optional[List[str]] = None,
|
162
|
+
wait_selector_state: SelectorWaitStates = "attached",
|
163
|
+
cookies: Optional[List[Dict]] = None,
|
164
|
+
google_search: bool = True,
|
165
|
+
extra_headers: Optional[Dict[str, str]] = None,
|
166
|
+
proxy: Optional[str | Dict[str, str]] = None,
|
167
|
+
os_randomize: bool = False,
|
168
|
+
disable_ads: bool = False,
|
169
|
+
geoip: bool = False,
|
170
|
+
custom_config: Optional[Dict] = None,
|
171
|
+
additional_args: Optional[Dict] = None,
|
309
172
|
) -> Response:
|
310
173
|
"""
|
311
174
|
Opens up a browser and do your request based on your chosen options below.
|
312
175
|
|
313
176
|
:param url: Target url.
|
314
|
-
:param headless: Run the browser in headless/hidden (default),
|
177
|
+
:param headless: Run the browser in headless/hidden (default), or headful/visible mode.
|
315
178
|
:param block_images: Prevent the loading of images through Firefox preferences.
|
316
179
|
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.
|
180
|
+
: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
181
|
Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`.
|
319
182
|
This can help save your proxy usage but be careful with this option as it makes some websites never finish loading.
|
320
183
|
:param block_webrtc: Blocks WebRTC entirely.
|
184
|
+
:param cookies: Set cookies for the next request.
|
321
185
|
: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
186
|
: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.
|
187
|
+
:param solve_cloudflare: Solves all 3 types of the Cloudflare's Turnstile wait page before returning the response to you.
|
188
|
+
:param allow_webgl: Enabled by default. Disabling WebGL is not recommended as many WAFs now check if WebGL is enabled.
|
327
189
|
:param network_idle: Wait for the page until there are no network connections for at least 500 ms.
|
190
|
+
:param disable_ads: Disabled by default, this installs the `uBlock Origin` addon on the browser if enabled.
|
328
191
|
: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
|
192
|
+
:param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object.
|
193
|
+
:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000
|
331
194
|
: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
|
-
|
195
|
+
:param wait_selector: Wait for a specific CSS selector to be in a specific state.
|
196
|
+
:param geoip: Recommended to use with proxies; Automatically use IP's longitude, latitude, timezone, country, locale, and spoof the WebRTC IP address.
|
197
|
+
It will also calculate and spoof the browser's language based on the distribution of language speakers in the target region.
|
198
|
+
:param wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
|
199
|
+
: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
200
|
: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
201
|
: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
202
|
: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
|
203
|
+
:param additional_args: Additional arguments to be passed to Camoufox as additional settings, and it takes higher priority than Scrapling's settings.
|
204
|
+
:return: A `Response` object.
|
340
205
|
"""
|
341
206
|
if not custom_config:
|
342
207
|
custom_config = {}
|
343
208
|
elif not isinstance(custom_config, dict):
|
344
|
-
ValueError(
|
209
|
+
ValueError(
|
210
|
+
f"The custom parser config must be of type dictionary, got {cls.__class__}"
|
211
|
+
)
|
345
212
|
|
346
|
-
|
213
|
+
async with AsyncStealthySession(
|
347
214
|
wait=wait,
|
215
|
+
max_pages=1,
|
348
216
|
proxy=proxy,
|
349
217
|
geoip=geoip,
|
350
218
|
addons=addons,
|
351
219
|
timeout=timeout,
|
220
|
+
cookies=cookies,
|
352
221
|
headless=headless,
|
353
222
|
humanize=humanize,
|
354
223
|
disable_ads=disable_ads,
|
@@ -361,82 +230,99 @@ class StealthyFetcher(BaseFetcher):
|
|
361
230
|
wait_selector=wait_selector,
|
362
231
|
google_search=google_search,
|
363
232
|
extra_headers=extra_headers,
|
233
|
+
solve_cloudflare=solve_cloudflare,
|
364
234
|
disable_resources=disable_resources,
|
365
235
|
wait_selector_state=wait_selector_state,
|
366
|
-
|
367
|
-
|
368
|
-
)
|
369
|
-
|
236
|
+
selector_config={**cls._generate_parser_arguments(), **custom_config},
|
237
|
+
additional_args=additional_args or {},
|
238
|
+
) as engine:
|
239
|
+
return await engine.fetch(url)
|
370
240
|
|
371
241
|
|
372
|
-
class
|
242
|
+
class DynamicFetcher(BaseFetcher):
|
373
243
|
"""A `Fetcher` class type that provide many options, all of them are based on PlayWright.
|
374
244
|
|
375
245
|
Using this Fetcher class, you can do requests with:
|
376
246
|
- 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
|
247
|
+
- 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
248
|
Some of the things stealth mode does include:
|
379
249
|
1) Patches the CDP runtime fingerprint.
|
380
250
|
2) Mimics some of the real browsers' properties by injecting several JS files and using custom options.
|
381
251
|
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.
|
252
|
+
4) Generates real browser's headers of the same type and same user OS, then append it to the request.
|
253
|
+
- 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
254
|
- NSTBrowser's docker browserless option by passing the CDP URL and enabling `nstbrowser_mode` option.
|
385
255
|
|
386
|
-
> Note that these are the main options with PlayWright but it can be mixed
|
256
|
+
> Note that these are the main options with PlayWright, but it can be mixed.
|
387
257
|
"""
|
258
|
+
|
388
259
|
@classmethod
|
389
260
|
def fetch(
|
390
|
-
|
391
|
-
|
392
|
-
|
393
|
-
|
394
|
-
|
395
|
-
|
396
|
-
|
397
|
-
|
398
|
-
|
261
|
+
cls,
|
262
|
+
url: str,
|
263
|
+
headless: bool = True,
|
264
|
+
google_search: bool = True,
|
265
|
+
hide_canvas: bool = False,
|
266
|
+
disable_webgl: bool = False,
|
267
|
+
real_chrome: bool = False,
|
268
|
+
stealth: bool = False,
|
269
|
+
wait: int | float = 0,
|
270
|
+
page_action: Optional[Callable] = None,
|
271
|
+
proxy: Optional[str | Dict[str, str]] = None,
|
272
|
+
locale: str = "en-US",
|
273
|
+
extra_headers: Optional[Dict[str, str]] = None,
|
274
|
+
useragent: Optional[str] = None,
|
275
|
+
cdp_url: Optional[str] = None,
|
276
|
+
timeout: int | float = 30000,
|
277
|
+
disable_resources: bool = False,
|
278
|
+
wait_selector: Optional[str] = None,
|
279
|
+
cookies: Optional[Iterable[Dict]] = None,
|
280
|
+
network_idle: bool = False,
|
281
|
+
wait_selector_state: SelectorWaitStates = "attached",
|
282
|
+
custom_config: Optional[Dict] = None,
|
399
283
|
) -> Response:
|
400
284
|
"""Opens up a browser and do your request based on your chosen options below.
|
401
285
|
|
402
286
|
:param url: Target url.
|
403
287
|
: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.
|
288
|
+
: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
289
|
Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`.
|
406
290
|
This can help save your proxy usage but be careful with this option as it makes some websites never finish loading.
|
407
291
|
:param useragent: Pass a useragent string to be used. Otherwise the fetcher will generate a real Useragent of the same browser and use it.
|
292
|
+
:param cookies: Set cookies for the next request.
|
408
293
|
: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`.
|
294
|
+
:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000
|
295
|
+
:param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object.
|
412
296
|
: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
|
297
|
+
:param wait_selector: Wait for a specific CSS selector to be in a specific state.
|
298
|
+
:param locale: Set the locale for the browser if wanted. The default value is `en-US`.
|
299
|
+
:param wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
|
415
300
|
:param stealth: Enables stealth mode, check the documentation to see what stealth mode does currently.
|
416
|
-
:param real_chrome: If you have
|
301
|
+
: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
302
|
:param hide_canvas: Add random noise to canvas operations to prevent fingerprinting.
|
418
303
|
:param disable_webgl: Disables WebGL and WebGL 2.0 support entirely.
|
419
|
-
:param
|
304
|
+
:param cdp_url: Instead of launching a new browser instance, connect to this CDP URL to control real browsers/NSTBrowser through CDP.
|
305
|
+
: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
306
|
: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
307
|
: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
308
|
: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
|
309
|
+
:return: A `Response` object.
|
427
310
|
"""
|
428
311
|
if not custom_config:
|
429
312
|
custom_config = {}
|
430
313
|
elif not isinstance(custom_config, dict):
|
431
|
-
ValueError(
|
314
|
+
raise ValueError(
|
315
|
+
f"The custom parser config must be of type dictionary, got {cls.__class__}"
|
316
|
+
)
|
432
317
|
|
433
|
-
|
318
|
+
with DynamicSession(
|
434
319
|
wait=wait,
|
435
320
|
proxy=proxy,
|
436
321
|
locale=locale,
|
437
322
|
timeout=timeout,
|
438
323
|
stealth=stealth,
|
439
324
|
cdp_url=cdp_url,
|
325
|
+
cookies=cookies,
|
440
326
|
headless=headless,
|
441
327
|
useragent=useragent,
|
442
328
|
real_chrome=real_chrome,
|
@@ -447,68 +333,82 @@ class PlayWrightFetcher(BaseFetcher):
|
|
447
333
|
extra_headers=extra_headers,
|
448
334
|
wait_selector=wait_selector,
|
449
335
|
disable_webgl=disable_webgl,
|
450
|
-
nstbrowser_mode=nstbrowser_mode,
|
451
|
-
nstbrowser_config=nstbrowser_config,
|
452
336
|
disable_resources=disable_resources,
|
453
337
|
wait_selector_state=wait_selector_state,
|
454
|
-
|
455
|
-
)
|
456
|
-
|
338
|
+
selector_config={**cls._generate_parser_arguments(), **custom_config},
|
339
|
+
) as session:
|
340
|
+
return session.fetch(url)
|
457
341
|
|
458
342
|
@classmethod
|
459
343
|
async def async_fetch(
|
460
|
-
|
461
|
-
|
462
|
-
|
463
|
-
|
464
|
-
|
465
|
-
|
466
|
-
|
467
|
-
|
468
|
-
|
344
|
+
cls,
|
345
|
+
url: str,
|
346
|
+
headless: bool = True,
|
347
|
+
google_search: bool = True,
|
348
|
+
hide_canvas: bool = False,
|
349
|
+
disable_webgl: bool = False,
|
350
|
+
real_chrome: bool = False,
|
351
|
+
stealth: bool = False,
|
352
|
+
wait: int | float = 0,
|
353
|
+
page_action: Optional[Callable] = None,
|
354
|
+
proxy: Optional[str | Dict[str, str]] = None,
|
355
|
+
locale: str = "en-US",
|
356
|
+
extra_headers: Optional[Dict[str, str]] = None,
|
357
|
+
useragent: Optional[str] = None,
|
358
|
+
cdp_url: Optional[str] = None,
|
359
|
+
timeout: int | float = 30000,
|
360
|
+
disable_resources: bool = False,
|
361
|
+
wait_selector: Optional[str] = None,
|
362
|
+
cookies: Optional[Iterable[Dict]] = None,
|
363
|
+
network_idle: bool = False,
|
364
|
+
wait_selector_state: SelectorWaitStates = "attached",
|
365
|
+
custom_config: Optional[Dict] = None,
|
469
366
|
) -> Response:
|
470
367
|
"""Opens up a browser and do your request based on your chosen options below.
|
471
368
|
|
472
369
|
:param url: Target url.
|
473
370
|
: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.
|
371
|
+
: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
372
|
Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`.
|
476
373
|
This can help save your proxy usage but be careful with this option as it makes some websites never finish loading.
|
477
374
|
:param useragent: Pass a useragent string to be used. Otherwise the fetcher will generate a real Useragent of the same browser and use it.
|
375
|
+
:param cookies: Set cookies for the next request.
|
478
376
|
: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`.
|
377
|
+
:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000
|
378
|
+
:param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object.
|
482
379
|
: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
|
380
|
+
:param wait_selector: Wait for a specific CSS selector to be in a specific state.
|
381
|
+
:param locale: Set the locale for the browser if wanted. The default value is `en-US`.
|
382
|
+
:param wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
|
485
383
|
:param stealth: Enables stealth mode, check the documentation to see what stealth mode does currently.
|
486
|
-
:param real_chrome: If you have
|
384
|
+
: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
385
|
:param hide_canvas: Add random noise to canvas operations to prevent fingerprinting.
|
488
386
|
:param disable_webgl: Disables WebGL and WebGL 2.0 support entirely.
|
489
|
-
:param
|
387
|
+
:param cdp_url: Instead of launching a new browser instance, connect to this CDP URL to control real browsers/NSTBrowser through CDP.
|
388
|
+
: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
389
|
: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
390
|
: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
391
|
: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
|
392
|
+
:return: A `Response` object.
|
497
393
|
"""
|
498
394
|
if not custom_config:
|
499
395
|
custom_config = {}
|
500
396
|
elif not isinstance(custom_config, dict):
|
501
|
-
ValueError(
|
397
|
+
raise ValueError(
|
398
|
+
f"The custom parser config must be of type dictionary, got {cls.__class__}"
|
399
|
+
)
|
502
400
|
|
503
|
-
|
401
|
+
async with AsyncDynamicSession(
|
504
402
|
wait=wait,
|
505
403
|
proxy=proxy,
|
506
404
|
locale=locale,
|
507
405
|
timeout=timeout,
|
508
406
|
stealth=stealth,
|
509
407
|
cdp_url=cdp_url,
|
408
|
+
cookies=cookies,
|
510
409
|
headless=headless,
|
511
410
|
useragent=useragent,
|
411
|
+
max_pages=1,
|
512
412
|
real_chrome=real_chrome,
|
513
413
|
page_action=page_action,
|
514
414
|
hide_canvas=hide_canvas,
|
@@ -517,17 +417,11 @@ class PlayWrightFetcher(BaseFetcher):
|
|
517
417
|
extra_headers=extra_headers,
|
518
418
|
wait_selector=wait_selector,
|
519
419
|
disable_webgl=disable_webgl,
|
520
|
-
nstbrowser_mode=nstbrowser_mode,
|
521
|
-
nstbrowser_config=nstbrowser_config,
|
522
420
|
disable_resources=disable_resources,
|
523
421
|
wait_selector_state=wait_selector_state,
|
524
|
-
|
525
|
-
)
|
526
|
-
|
422
|
+
selector_config={**cls._generate_parser_arguments(), **custom_config},
|
423
|
+
) as session:
|
424
|
+
return await session.fetch(url)
|
527
425
|
|
528
426
|
|
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)
|
427
|
+
PlayWrightFetcher = DynamicFetcher # For backward-compatibility
|