crawlee 1.1.1b1__py3-none-any.whl → 1.1.2b4__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.
Potentially problematic release.
This version of crawlee might be problematic. Click here for more details.
- crawlee/_types.py +20 -1
- crawlee/_utils/file.py +7 -0
- crawlee/_utils/time.py +41 -1
- crawlee/crawlers/__init__.py +2 -1
- crawlee/crawlers/_abstract_http/__init__.py +2 -1
- crawlee/crawlers/_abstract_http/_abstract_http_crawler.py +46 -12
- crawlee/crawlers/_basic/_basic_crawler.py +107 -101
- crawlee/crawlers/_beautifulsoup/_beautifulsoup_crawler.py +2 -2
- crawlee/crawlers/_parsel/_parsel_crawler.py +2 -2
- crawlee/crawlers/_playwright/_playwright_crawler.py +40 -10
- crawlee/crawlers/_playwright/_playwright_http_client.py +7 -1
- crawlee/http_clients/_base.py +4 -0
- crawlee/http_clients/_curl_impersonate.py +12 -0
- crawlee/http_clients/_httpx.py +16 -6
- crawlee/http_clients/_impit.py +25 -10
- crawlee/storage_clients/_file_system/_dataset_client.py +2 -2
- crawlee/storage_clients/_file_system/_key_value_store_client.py +3 -3
- crawlee/storage_clients/_file_system/_request_queue_client.py +3 -3
- crawlee/storage_clients/_sql/_storage_client.py +0 -9
- {crawlee-1.1.1b1.dist-info → crawlee-1.1.2b4.dist-info}/METADATA +4 -3
- {crawlee-1.1.1b1.dist-info → crawlee-1.1.2b4.dist-info}/RECORD +24 -24
- {crawlee-1.1.1b1.dist-info → crawlee-1.1.2b4.dist-info}/WHEEL +1 -1
- {crawlee-1.1.1b1.dist-info → crawlee-1.1.2b4.dist-info}/entry_points.txt +0 -0
- {crawlee-1.1.1b1.dist-info → crawlee-1.1.2b4.dist-info}/licenses/LICENSE +0 -0
|
@@ -5,7 +5,7 @@ crawlee/_consts.py,sha256=RQ96gx7V-WPH91cVsMUz76X5UZUNDNhCudtlyGkxFVk,133
|
|
|
5
5
|
crawlee/_log_config.py,sha256=VyxoEfWCq_9fyicmmJbjiZ5KC91onMcAtX2L4oKX4m4,5999
|
|
6
6
|
crawlee/_request.py,sha256=fnUofyFMV3HJwfcLjYr2BCZ5K9mEwl6vZd8Pr309wCE,16458
|
|
7
7
|
crawlee/_service_locator.py,sha256=SJ8ABYtclBl7rz8kfZ2jZkIgKq5oNIoGT7WmN8ApTzo,5058
|
|
8
|
-
crawlee/_types.py,sha256=
|
|
8
|
+
crawlee/_types.py,sha256=93yoGr_KqMDIkq3__3QYpIAJmEzZvDoilHAF7_X4J4A,29933
|
|
9
9
|
crawlee/configuration.py,sha256=DWS2z1FC6Ua93W2tStK3R1ZKZbZjVQYWGiGFbZFaRtA,8064
|
|
10
10
|
crawlee/errors.py,sha256=RhFNA_uT615nVBHf9TylpX5YWwtDuHUUEV8LPT4CYa4,3878
|
|
11
11
|
crawlee/proxy_configuration.py,sha256=rqf67yerXvLvraBaAHW04nvf5ECze3wMQbK7LlqXucM,10386
|
|
@@ -24,7 +24,7 @@ crawlee/_utils/console.py,sha256=vAIM8AO7cT-HdXg44eR8zQyHAHk8X8G7J1KKFCBL2LY,224
|
|
|
24
24
|
crawlee/_utils/context.py,sha256=FsRh394RpNZTRovuVHVlyVTZ8AbSLGe-K7RpLgU9AX8,1726
|
|
25
25
|
crawlee/_utils/crypto.py,sha256=tYzn2z91KgV3ugxz4CKtSTcCjW-3FC8un7hpDNCl6rs,757
|
|
26
26
|
crawlee/_utils/docs.py,sha256=S09-3xAQAlUvrmPpBXVJpE8wblB8LtS6QduLNncfqdQ,1130
|
|
27
|
-
crawlee/_utils/file.py,sha256=
|
|
27
|
+
crawlee/_utils/file.py,sha256=FJHTC25qSWQs3ZhCZrLgs0cUwA9K81MlQRGEmcWKAQU,5758
|
|
28
28
|
crawlee/_utils/globs.py,sha256=SGX2J35Kqw7yZnSS5c4mLz9UD8c77PF0IoCgXQM5uiw,5310
|
|
29
29
|
crawlee/_utils/html_to_text.py,sha256=1iykT-OXd2xXNy7isHVWHqPxe23X82CGQBHIfbZbZkY,902
|
|
30
30
|
crawlee/_utils/models.py,sha256=EqM50Uc-xvxKlLCLA2lPpRduzfKvT0z_-Q-UWG8aTRQ,1955
|
|
@@ -35,7 +35,7 @@ crawlee/_utils/requests.py,sha256=yOjai7bHR9_duPJ0ck-L76y9AnKZr49JBfSOQv9kvJc,50
|
|
|
35
35
|
crawlee/_utils/robots.py,sha256=DBU5ni4Y-p7bIKMbLd_ws8wgHSFc4K8zPVF3JvH_pkw,4661
|
|
36
36
|
crawlee/_utils/sitemap.py,sha256=UI9EJiFiyFvV5_flVUtdsEVz8ZsJeRERPtcx8ZsqjTU,16632
|
|
37
37
|
crawlee/_utils/system.py,sha256=tA8AP__9vsJ9OTLTnAYAKkxc8U5-IEna0N_hqYBybUo,4294
|
|
38
|
-
crawlee/_utils/time.py,sha256=
|
|
38
|
+
crawlee/_utils/time.py,sha256=awyzUqMvoC3BrEDINHaGPaM-u98AW0UtQqQsVJPAnsA,3899
|
|
39
39
|
crawlee/_utils/try_import.py,sha256=QI_58ifc2l0Rxehzu6xcofQrRAVeLzZuBTTTHttLl8s,1310
|
|
40
40
|
crawlee/_utils/urls.py,sha256=fEYXJxBT02f-DIYKF_h7PdaKAShfXBs99-dHDjDX03A,1725
|
|
41
41
|
crawlee/_utils/wait.py,sha256=RfiXhp5VUBxOEtEMtru7_jNfKDr2BJCcFge5qGg2gxk,2848
|
|
@@ -49,11 +49,11 @@ crawlee/browsers/_playwright_browser_controller.py,sha256=W6G5MjZpg9IcZoHts6lTML
|
|
|
49
49
|
crawlee/browsers/_playwright_browser_plugin.py,sha256=A1qa1nJhTSKNP9uOiO-oGzR7VGlnOMo0A0YNedccb2A,8869
|
|
50
50
|
crawlee/browsers/_types.py,sha256=ZnDgJHeQNSd_s_mXhgQnAf09c2smuiXC31VbawHHXUM,436
|
|
51
51
|
crawlee/browsers/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
52
|
-
crawlee/crawlers/__init__.py,sha256=
|
|
52
|
+
crawlee/crawlers/__init__.py,sha256=jNFMsPizSgCN0ARYSmHs9Ppk8yvGgjUH5PxUeDchljE,2386
|
|
53
53
|
crawlee/crawlers/_types.py,sha256=xbGTJQirgz5wUbfr12afMR4q-_5AWP7ngF2e8K5P8l0,355
|
|
54
54
|
crawlee/crawlers/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
55
|
-
crawlee/crawlers/_abstract_http/__init__.py,sha256=
|
|
56
|
-
crawlee/crawlers/_abstract_http/_abstract_http_crawler.py,sha256=
|
|
55
|
+
crawlee/crawlers/_abstract_http/__init__.py,sha256=h8jVWcPbDXzWHill1Vm7J7iliJW0hIrea0gkg-Hkb-M,319
|
|
56
|
+
crawlee/crawlers/_abstract_http/_abstract_http_crawler.py,sha256=AfrEea3Ez2RvS6G6BFBfB6gg9aAFu-84RWqWryNHFrc,12977
|
|
57
57
|
crawlee/crawlers/_abstract_http/_abstract_http_parser.py,sha256=Y5o_hiW_0mQAte5GFqkUxscwKEFpWrBYRsLKP1cfBwE,3521
|
|
58
58
|
crawlee/crawlers/_abstract_http/_http_crawling_context.py,sha256=Rno_uJ8ivmyRxFQv2MyY_z9B5WPHSEd5MAPz31_1ZIo,2179
|
|
59
59
|
crawlee/crawlers/_abstract_http/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
@@ -65,13 +65,13 @@ crawlee/crawlers/_adaptive_playwright/_rendering_type_predictor.py,sha256=TM4mkb
|
|
|
65
65
|
crawlee/crawlers/_adaptive_playwright/_result_comparator.py,sha256=NAfw5VKzTnkvARtLr_zrZj6UGeMp05Voc6Oi8oPxU3w,1747
|
|
66
66
|
crawlee/crawlers/_adaptive_playwright/_utils.py,sha256=EUYVz5i2YkLpL_gbVRp9BAD5u6w1xJ_AFzc_qB9bdDQ,1102
|
|
67
67
|
crawlee/crawlers/_basic/__init__.py,sha256=LPln8SiBBXSMqrApiFUfpqz3hvqxN5HUa1cHQXMVKgU,280
|
|
68
|
-
crawlee/crawlers/_basic/_basic_crawler.py,sha256
|
|
68
|
+
crawlee/crawlers/_basic/_basic_crawler.py,sha256=uL9QDGis__8z0W0u6ShsJMpvlrMmIi3MaucOvIxh0iI,73437
|
|
69
69
|
crawlee/crawlers/_basic/_basic_crawling_context.py,sha256=fjxm2RQXMDkDlWu38dQ3xn5rrGUOhJXkXiqkgbFJFk4,155
|
|
70
70
|
crawlee/crawlers/_basic/_context_pipeline.py,sha256=vM8EEvnCoguERjRV3oyrxUq2Ln2F9DzY7P5dAEiuMHo,5869
|
|
71
71
|
crawlee/crawlers/_basic/_logging_utils.py,sha256=jp5mEwSq5a_BgzUhNPJ9WrIDcoIeYGbeHstcRqCcP0s,3093
|
|
72
72
|
crawlee/crawlers/_basic/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
73
73
|
crawlee/crawlers/_beautifulsoup/__init__.py,sha256=7pL273ashA7yYDrH6nokYZ7SAMUAezilGIWdfThi_Co,822
|
|
74
|
-
crawlee/crawlers/_beautifulsoup/_beautifulsoup_crawler.py,sha256=
|
|
74
|
+
crawlee/crawlers/_beautifulsoup/_beautifulsoup_crawler.py,sha256=Q8Sb_lflpdYIwDZ1fIeuquPzdDG2zCnKsrcj8fe8n6k,3056
|
|
75
75
|
crawlee/crawlers/_beautifulsoup/_beautifulsoup_crawling_context.py,sha256=CMHQbYmXdhnXSo3hjtmAqWPH2lEaoVHzwPY2Ka85s70,1149
|
|
76
76
|
crawlee/crawlers/_beautifulsoup/_beautifulsoup_parser.py,sha256=egCBcaE6RaQoJOFuxex_McItCd4Ddd3ZDE-2DVGictA,1661
|
|
77
77
|
crawlee/crawlers/_beautifulsoup/_utils.py,sha256=xUJM7Y0RGlTEe0TJe252uuIdjk8gwBFjuhQnRG7-jv4,3127
|
|
@@ -80,14 +80,14 @@ crawlee/crawlers/_http/__init__.py,sha256=BY6KKY1eD8CWDFfurJDIgcnFIfgXAVuMHKSL3w
|
|
|
80
80
|
crawlee/crawlers/_http/_http_crawler.py,sha256=HoCTku4FL9EN3WMlzbZNbb2BtXedP487CN0JlObsoGg,2041
|
|
81
81
|
crawlee/crawlers/_http/_http_parser.py,sha256=Bfe3TEz6i5UhONO2qfyw2p31QoVoXbvGci3T3HeObiU,1495
|
|
82
82
|
crawlee/crawlers/_parsel/__init__.py,sha256=c_FveWxCuaEaG2HAYlaN9N_aPEaVdpaYVMsIcCcTdnU,617
|
|
83
|
-
crawlee/crawlers/_parsel/_parsel_crawler.py,sha256=
|
|
83
|
+
crawlee/crawlers/_parsel/_parsel_crawler.py,sha256=Aolo96FU_U3nsEjGoxEothgF7pVuoXLkhRmNWgKzGYg,2717
|
|
84
84
|
crawlee/crawlers/_parsel/_parsel_crawling_context.py,sha256=sZB26RcRLjSoD15myEOMPeolIN7apG76aqRmKQvEep8,1142
|
|
85
85
|
crawlee/crawlers/_parsel/_parsel_parser.py,sha256=yWBfuXUHMriK4DRnyrXTQoGeqX5WV9bOEkBp_g0YCvQ,1540
|
|
86
86
|
crawlee/crawlers/_parsel/_utils.py,sha256=MbRwx-cdjlq1zLzFYf64M3spOGQ6yxum4FvP0sdqA_Q,2693
|
|
87
87
|
crawlee/crawlers/_playwright/__init__.py,sha256=6Cahe6VEF82o8CYiP8Cmp58Cmb6Rb8uMeyy7wnwe5ms,837
|
|
88
|
-
crawlee/crawlers/_playwright/_playwright_crawler.py,sha256=
|
|
88
|
+
crawlee/crawlers/_playwright/_playwright_crawler.py,sha256=PHoU2qn_SlUM0mGeiPVfLPaKgXIjzvPn-ZDI3rdGVII,25546
|
|
89
89
|
crawlee/crawlers/_playwright/_playwright_crawling_context.py,sha256=Oi0tMBXHaEDlFjqG01DzgB7Ck52bjVjz-X__eMioxas,1249
|
|
90
|
-
crawlee/crawlers/_playwright/_playwright_http_client.py,sha256=
|
|
90
|
+
crawlee/crawlers/_playwright/_playwright_http_client.py,sha256=4mvaCI9Zum7znbm0F-ZZ6T1FEqZ-N-cvPOk1iqtcUSo,4164
|
|
91
91
|
crawlee/crawlers/_playwright/_playwright_pre_nav_crawling_context.py,sha256=fEI2laWhmJdWiGoMF5JBLBsim9NtENfagZt6FFd2Rgo,1387
|
|
92
92
|
crawlee/crawlers/_playwright/_types.py,sha256=hMKA9K9gjzQuwwbnmmfJsQrwR-kq235jH-WBXWeqkGo,2174
|
|
93
93
|
crawlee/crawlers/_playwright/_utils.py,sha256=FQ_-LYo7DGHsNHRrTtWt3mC06VzQvQ2wkGqpA2wBzYU,3441
|
|
@@ -104,10 +104,10 @@ crawlee/fingerprint_suite/_header_generator.py,sha256=9X9FbStehXdw-FZc_D0y-nLk1B
|
|
|
104
104
|
crawlee/fingerprint_suite/_types.py,sha256=7n2LJTiL2XvL-H4G-Y26Uoq5-ZXzH07Dq4o50uhMa-w,2423
|
|
105
105
|
crawlee/fingerprint_suite/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
106
106
|
crawlee/http_clients/__init__.py,sha256=OQFhR9F8BrdlIaS5aRS7hvgQ0tKJPQ8FiyYPualyQcU,890
|
|
107
|
-
crawlee/http_clients/_base.py,sha256=
|
|
108
|
-
crawlee/http_clients/_curl_impersonate.py,sha256=
|
|
109
|
-
crawlee/http_clients/_httpx.py,sha256=
|
|
110
|
-
crawlee/http_clients/_impit.py,sha256=
|
|
107
|
+
crawlee/http_clients/_base.py,sha256=sz-NCgGyRKhNz2tPR7Zq10iYQ8Itig-fls4h7GMHhNM,7593
|
|
108
|
+
crawlee/http_clients/_curl_impersonate.py,sha256=a_1QQ04Tk_d5t2mIjxEKPvjF7zTn3q74QosuBjG8Wkc,11847
|
|
109
|
+
crawlee/http_clients/_httpx.py,sha256=abRe2YjQUfIrtmOwOAB72viwd8CF0V2mAXQceLuIWvo,12375
|
|
110
|
+
crawlee/http_clients/_impit.py,sha256=wEfDSOGIOmfLUkmLXAmZkiM5wp4PltUv-oH7zq2NMfQ,9434
|
|
111
111
|
crawlee/otel/__init__.py,sha256=g5y1tJfpDKfcIPGcKBztMgP6sptum-vJrtemeR8_-co,108
|
|
112
112
|
crawlee/otel/crawler_instrumentor.py,sha256=yC367A1NnAdhOanvym2zfiu4H4BskUslrib0GcHiVJs,6865
|
|
113
113
|
crawlee/project_template/cookiecutter.json,sha256=dJeYxLx5QEy2DCzXsDpqJQJlIJ3nw42lJrclZFoSZ8w,622
|
|
@@ -159,9 +159,9 @@ crawlee/storage_clients/_base/_request_queue_client.py,sha256=cgM4yk6xJwgfzP-xaN
|
|
|
159
159
|
crawlee/storage_clients/_base/_storage_client.py,sha256=RvmKCV1U9_KxyG7n8xhClm2vwD2SKChWIiBLk6cuqw0,3523
|
|
160
160
|
crawlee/storage_clients/_base/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
161
161
|
crawlee/storage_clients/_file_system/__init__.py,sha256=w3twfwz5YeLYeu_70pNPBRINS2wXRvzOMvA1hUDYgf0,387
|
|
162
|
-
crawlee/storage_clients/_file_system/_dataset_client.py,sha256=
|
|
163
|
-
crawlee/storage_clients/_file_system/_key_value_store_client.py,sha256=
|
|
164
|
-
crawlee/storage_clients/_file_system/_request_queue_client.py,sha256=
|
|
162
|
+
crawlee/storage_clients/_file_system/_dataset_client.py,sha256=DTRYlm37VV7FuowenG0JoqiQdH5AMg9G0O1PPJJO-u0,17781
|
|
163
|
+
crawlee/storage_clients/_file_system/_key_value_store_client.py,sha256=zPXCKPm6w8UYLYwSOuAoc4uoFswJjTAoWMulucvFBiI,18745
|
|
164
|
+
crawlee/storage_clients/_file_system/_request_queue_client.py,sha256=3dn9DM750ftuUzDCp_Uj56tNakYb93nhmeSo2LjPeV0,34039
|
|
165
165
|
crawlee/storage_clients/_file_system/_storage_client.py,sha256=My63uc513kfUPe5X-PTYWBRe9xUGnkLqJN7IcsQd2yw,3293
|
|
166
166
|
crawlee/storage_clients/_file_system/_utils.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
167
167
|
crawlee/storage_clients/_file_system/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
@@ -189,7 +189,7 @@ crawlee/storage_clients/_sql/_dataset_client.py,sha256=tiJVvOPZgc7cy4kGfWnun-g2T
|
|
|
189
189
|
crawlee/storage_clients/_sql/_db_models.py,sha256=KzA-R_L6zv9gqQg7B27mF-fERNJuMUEnewV9iofmTnI,9812
|
|
190
190
|
crawlee/storage_clients/_sql/_key_value_store_client.py,sha256=LnVLWhOjo4LdvtCac4fwuf__DgEQjlqSxz8KkjY3Qx4,11311
|
|
191
191
|
crawlee/storage_clients/_sql/_request_queue_client.py,sha256=OlvAOwEoYY5f4NO7BdhLFRT_i_E3YzJDb_ptKKK2huY,29478
|
|
192
|
-
crawlee/storage_clients/_sql/_storage_client.py,sha256=
|
|
192
|
+
crawlee/storage_clients/_sql/_storage_client.py,sha256=ITtMpwfotIW4SZjO4rycB5wfMKaqTAJgMvzcUZxckrk,10905
|
|
193
193
|
crawlee/storage_clients/_sql/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
194
194
|
crawlee/storages/__init__.py,sha256=wc2eioyCKAAYrg4N7cshpjC-UbE23OzGar9nK_kteSY,186
|
|
195
195
|
crawlee/storages/_base.py,sha256=zUOcMJTg8MAzq-m9X1NJcWncCfxzI5mb5MyY35WAkMk,2310
|
|
@@ -199,8 +199,8 @@ crawlee/storages/_request_queue.py,sha256=bjBOGbpMaGUsqJPVB-JD2VShziPAYMI-GvWKKp
|
|
|
199
199
|
crawlee/storages/_storage_instance_manager.py,sha256=72n0YlPwNpSQDJSPf4TxnI2GvIK6L-ZiTmHRbFcoVU0,8164
|
|
200
200
|
crawlee/storages/_utils.py,sha256=Yz-5tEBYKYCFJemYT29--uGJqoJLApLDLgPcsnbifRw,439
|
|
201
201
|
crawlee/storages/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
202
|
-
crawlee-1.1.
|
|
203
|
-
crawlee-1.1.
|
|
204
|
-
crawlee-1.1.
|
|
205
|
-
crawlee-1.1.
|
|
206
|
-
crawlee-1.1.
|
|
202
|
+
crawlee-1.1.2b4.dist-info/METADATA,sha256=xHqoYBVYvhy6i_bpLm0VF44jWovuibr2Xl2bl4wfRPU,29508
|
|
203
|
+
crawlee-1.1.2b4.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
|
|
204
|
+
crawlee-1.1.2b4.dist-info/entry_points.txt,sha256=1p65X3dA-cYvzjtlxLL6Kn1wpY-3uEDVqJLp53uNPeo,45
|
|
205
|
+
crawlee-1.1.2b4.dist-info/licenses/LICENSE,sha256=AsFjHssKjj4LGd2ZCqXn6FBzMqcWdjQre1byPPSypVw,11355
|
|
206
|
+
crawlee-1.1.2b4.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|