apify 1.7.1b1__py3-none-any.whl → 2.2.1b1__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 apify might be problematic. Click here for more details.
- apify/__init__.py +33 -4
- apify/_actor.py +1074 -0
- apify/_configuration.py +370 -0
- apify/_consts.py +10 -0
- apify/_crypto.py +31 -27
- apify/_models.py +117 -0
- apify/_platform_event_manager.py +231 -0
- apify/_proxy_configuration.py +320 -0
- apify/_utils.py +18 -484
- apify/apify_storage_client/__init__.py +3 -0
- apify/apify_storage_client/_apify_storage_client.py +68 -0
- apify/apify_storage_client/_dataset_client.py +190 -0
- apify/apify_storage_client/_dataset_collection_client.py +51 -0
- apify/apify_storage_client/_key_value_store_client.py +94 -0
- apify/apify_storage_client/_key_value_store_collection_client.py +51 -0
- apify/apify_storage_client/_request_queue_client.py +176 -0
- apify/apify_storage_client/_request_queue_collection_client.py +51 -0
- apify/apify_storage_client/py.typed +0 -0
- apify/log.py +22 -105
- apify/scrapy/__init__.py +11 -3
- apify/scrapy/middlewares/__init__.py +3 -1
- apify/scrapy/middlewares/apify_proxy.py +29 -27
- apify/scrapy/middlewares/py.typed +0 -0
- apify/scrapy/pipelines/__init__.py +3 -1
- apify/scrapy/pipelines/actor_dataset_push.py +6 -3
- apify/scrapy/pipelines/py.typed +0 -0
- apify/scrapy/py.typed +0 -0
- apify/scrapy/requests.py +60 -58
- apify/scrapy/scheduler.py +28 -19
- apify/scrapy/utils.py +10 -32
- apify/storages/__init__.py +4 -10
- apify/storages/_request_list.py +150 -0
- apify/storages/py.typed +0 -0
- apify-2.2.1b1.dist-info/METADATA +211 -0
- apify-2.2.1b1.dist-info/RECORD +38 -0
- {apify-1.7.1b1.dist-info → apify-2.2.1b1.dist-info}/WHEEL +1 -2
- apify/_memory_storage/__init__.py +0 -3
- apify/_memory_storage/file_storage_utils.py +0 -71
- apify/_memory_storage/memory_storage_client.py +0 -219
- apify/_memory_storage/resource_clients/__init__.py +0 -19
- apify/_memory_storage/resource_clients/base_resource_client.py +0 -141
- apify/_memory_storage/resource_clients/base_resource_collection_client.py +0 -114
- apify/_memory_storage/resource_clients/dataset.py +0 -452
- apify/_memory_storage/resource_clients/dataset_collection.py +0 -48
- apify/_memory_storage/resource_clients/key_value_store.py +0 -533
- apify/_memory_storage/resource_clients/key_value_store_collection.py +0 -48
- apify/_memory_storage/resource_clients/request_queue.py +0 -466
- apify/_memory_storage/resource_clients/request_queue_collection.py +0 -48
- apify/actor.py +0 -1351
- apify/config.py +0 -127
- apify/consts.py +0 -67
- apify/event_manager.py +0 -236
- apify/proxy_configuration.py +0 -365
- apify/storages/base_storage.py +0 -181
- apify/storages/dataset.py +0 -494
- apify/storages/key_value_store.py +0 -257
- apify/storages/request_queue.py +0 -602
- apify/storages/storage_client_manager.py +0 -72
- apify-1.7.1b1.dist-info/METADATA +0 -149
- apify-1.7.1b1.dist-info/RECORD +0 -41
- apify-1.7.1b1.dist-info/top_level.txt +0 -1
- {apify-1.7.1b1.dist-info → apify-2.2.1b1.dist-info}/LICENSE +0 -0
apify-1.7.1b1.dist-info/METADATA
DELETED
|
@@ -1,149 +0,0 @@
|
|
|
1
|
-
Metadata-Version: 2.1
|
|
2
|
-
Name: apify
|
|
3
|
-
Version: 1.7.1b1
|
|
4
|
-
Summary: Apify SDK for Python
|
|
5
|
-
Author-email: "Apify Technologies s.r.o." <support@apify.com>
|
|
6
|
-
License: Apache Software License
|
|
7
|
-
Project-URL: Homepage, https://docs.apify.com/sdk/python/
|
|
8
|
-
Project-URL: Documentation, https://docs.apify.com/sdk/python/
|
|
9
|
-
Project-URL: Source, https://github.com/apify/apify-sdk-python
|
|
10
|
-
Project-URL: Issue tracker, https://github.com/apify/apify-sdk-python/issues
|
|
11
|
-
Project-URL: Changelog, https://github.com/apify/apify-sdk-python/blob/master/CHANGELOG.md
|
|
12
|
-
Project-URL: Apify Homepage, https://apify.com
|
|
13
|
-
Keywords: apify,sdk,actor,scraping,automation
|
|
14
|
-
Classifier: Development Status :: 5 - Production/Stable
|
|
15
|
-
Classifier: Intended Audience :: Developers
|
|
16
|
-
Classifier: License :: OSI Approved :: Apache Software License
|
|
17
|
-
Classifier: Operating System :: OS Independent
|
|
18
|
-
Classifier: Programming Language :: Python :: 3.8
|
|
19
|
-
Classifier: Programming Language :: Python :: 3.9
|
|
20
|
-
Classifier: Programming Language :: Python :: 3.10
|
|
21
|
-
Classifier: Programming Language :: Python :: 3.11
|
|
22
|
-
Classifier: Programming Language :: Python :: 3.12
|
|
23
|
-
Classifier: Topic :: Software Development :: Libraries
|
|
24
|
-
Requires-Python: >=3.8
|
|
25
|
-
Description-Content-Type: text/markdown
|
|
26
|
-
License-File: LICENSE
|
|
27
|
-
Requires-Dist: apify-client ~=1.6.2
|
|
28
|
-
Requires-Dist: apify-shared ~=1.1.1
|
|
29
|
-
Requires-Dist: aiofiles >=22.1.0
|
|
30
|
-
Requires-Dist: aioshutil >=1.0
|
|
31
|
-
Requires-Dist: colorama >=0.4.6
|
|
32
|
-
Requires-Dist: cryptography >=39.0.0
|
|
33
|
-
Requires-Dist: httpx >=0.24.1
|
|
34
|
-
Requires-Dist: psutil >=5.9.5
|
|
35
|
-
Requires-Dist: pyee >=11.0.1
|
|
36
|
-
Requires-Dist: sortedcollections >=2.0.1
|
|
37
|
-
Requires-Dist: typing-extensions >=4.1.0
|
|
38
|
-
Requires-Dist: websockets >=10.1
|
|
39
|
-
Provides-Extra: dev
|
|
40
|
-
Requires-Dist: build ~=1.0.3 ; extra == 'dev'
|
|
41
|
-
Requires-Dist: filelock ~=3.12.4 ; extra == 'dev'
|
|
42
|
-
Requires-Dist: mypy ~=1.7.1 ; extra == 'dev'
|
|
43
|
-
Requires-Dist: pre-commit ~=3.4.0 ; extra == 'dev'
|
|
44
|
-
Requires-Dist: pydoc-markdown ~=4.8.2 ; extra == 'dev'
|
|
45
|
-
Requires-Dist: pytest ~=7.4.2 ; extra == 'dev'
|
|
46
|
-
Requires-Dist: pytest-asyncio ~=0.21.0 ; extra == 'dev'
|
|
47
|
-
Requires-Dist: pytest-cov ~=4.1.0 ; extra == 'dev'
|
|
48
|
-
Requires-Dist: pytest-only ~=2.0.0 ; extra == 'dev'
|
|
49
|
-
Requires-Dist: pytest-timeout ~=2.2.0 ; extra == 'dev'
|
|
50
|
-
Requires-Dist: pytest-xdist ~=3.3.1 ; extra == 'dev'
|
|
51
|
-
Requires-Dist: respx ~=0.20.1 ; extra == 'dev'
|
|
52
|
-
Requires-Dist: ruff ~=0.1.13 ; extra == 'dev'
|
|
53
|
-
Requires-Dist: twine ~=4.0.2 ; extra == 'dev'
|
|
54
|
-
Requires-Dist: types-aiofiles ~=23.2.0.0 ; extra == 'dev'
|
|
55
|
-
Requires-Dist: types-colorama ~=0.4.15.12 ; extra == 'dev'
|
|
56
|
-
Requires-Dist: types-psutil ~=5.9.5.17 ; extra == 'dev'
|
|
57
|
-
Provides-Extra: scrapy
|
|
58
|
-
Requires-Dist: scrapy >=2.11.0 ; extra == 'scrapy'
|
|
59
|
-
|
|
60
|
-
# Apify SDK for Python
|
|
61
|
-
|
|
62
|
-
The Apify SDK for Python is the official library to create [Apify Actors](https://docs.apify.com/platform/actors)
|
|
63
|
-
in Python. It provides useful features like Actor lifecycle management, local storage emulation, and Actor
|
|
64
|
-
event handling.
|
|
65
|
-
|
|
66
|
-
If you just need to access the [Apify API](https://docs.apify.com/api/v2) from your Python applications,
|
|
67
|
-
check out the [Apify Client for Python](https://docs.apify.com/api/client/python) instead.
|
|
68
|
-
|
|
69
|
-
## Installation
|
|
70
|
-
|
|
71
|
-
The Apify SDK for Python is available on PyPI as the `apify` package.
|
|
72
|
-
For default installation, using Pip, run the following:
|
|
73
|
-
|
|
74
|
-
```bash
|
|
75
|
-
pip install apify
|
|
76
|
-
```
|
|
77
|
-
|
|
78
|
-
For users interested in integrating Apify with Scrapy, we provide a package extra called `scrapy`.
|
|
79
|
-
To install Apify with the `scrapy` extra, use the following command:
|
|
80
|
-
|
|
81
|
-
```bash
|
|
82
|
-
pip install apify[scrapy]
|
|
83
|
-
```
|
|
84
|
-
|
|
85
|
-
## Documentation
|
|
86
|
-
|
|
87
|
-
For usage instructions, check the documentation on [Apify Docs](https://docs.apify.com/sdk/python/).
|
|
88
|
-
|
|
89
|
-
## Example
|
|
90
|
-
|
|
91
|
-
```python
|
|
92
|
-
from apify import Actor
|
|
93
|
-
from bs4 import BeautifulSoup
|
|
94
|
-
from httpx import AsyncClient
|
|
95
|
-
|
|
96
|
-
async def main() -> None:
|
|
97
|
-
async with Actor:
|
|
98
|
-
# Read the input parameters from the Actor input
|
|
99
|
-
actor_input = await Actor.get_input()
|
|
100
|
-
# Fetch the HTTP response from the specified URL
|
|
101
|
-
async with AsyncClient() as client:
|
|
102
|
-
response = await client.get(actor_input['url'])
|
|
103
|
-
# Process the HTML content
|
|
104
|
-
soup = BeautifulSoup(response.content, 'html.parser')
|
|
105
|
-
# Push the extracted data
|
|
106
|
-
await Actor.push_data({
|
|
107
|
-
'url': actor_input['url'],
|
|
108
|
-
'title': soup.title.string,
|
|
109
|
-
})
|
|
110
|
-
```
|
|
111
|
-
|
|
112
|
-
## What are Actors?
|
|
113
|
-
|
|
114
|
-
Actors are serverless cloud programs that can do almost anything a human can do in a web browser.
|
|
115
|
-
They can do anything from small tasks such as filling in forms or unsubscribing from online services,
|
|
116
|
-
all the way up to scraping and processing vast numbers of web pages.
|
|
117
|
-
|
|
118
|
-
They can be run either locally, or on the [Apify platform](https://docs.apify.com/platform/),
|
|
119
|
-
where you can run them at scale, monitor them, schedule them, or publish and monetize them.
|
|
120
|
-
|
|
121
|
-
If you're new to Apify, learn [what is Apify](https://docs.apify.com/platform/about)
|
|
122
|
-
in the Apify platform documentation.
|
|
123
|
-
|
|
124
|
-
## Creating Actors
|
|
125
|
-
|
|
126
|
-
To create and run Actors through Apify Console,
|
|
127
|
-
see the [Console documentation](https://docs.apify.com/academy/getting-started/creating-actors#choose-your-template).
|
|
128
|
-
|
|
129
|
-
To create and run Python Actors locally, check the documentation for
|
|
130
|
-
[how to create and run Python Actors locally](https://docs.apify.com/sdk/python/docs/overview/running-locally).
|
|
131
|
-
|
|
132
|
-
## Guides
|
|
133
|
-
|
|
134
|
-
To see how you can use the Apify SDK with other popular libraries used for web scraping,
|
|
135
|
-
check out our guides for using
|
|
136
|
-
[Requests and HTTPX](https://docs.apify.com/sdk/python/docs/guides/requests-and-httpx),
|
|
137
|
-
[Beautiful Soup](https://docs.apify.com/sdk/python/docs/guides/beautiful-soup),
|
|
138
|
-
[Playwright](https://docs.apify.com/sdk/python/docs/guides/playwright),
|
|
139
|
-
[Selenium](https://docs.apify.com/sdk/python/docs/guides/selenium),
|
|
140
|
-
or [Scrapy](https://docs.apify.com/sdk/python/docs/guides/scrapy).
|
|
141
|
-
|
|
142
|
-
## Usage concepts
|
|
143
|
-
|
|
144
|
-
To learn more about the features of the Apify SDK and how to use them,
|
|
145
|
-
check out the Usage Concepts section in the sidebar,
|
|
146
|
-
particularly the guides for the [Actor lifecycle](https://docs.apify.com/sdk/python/docs/concepts/actor-lifecycle),
|
|
147
|
-
[working with storages](https://docs.apify.com/sdk/python/docs/concepts/storages),
|
|
148
|
-
[handling Actor events](https://docs.apify.com/sdk/python/docs/concepts/actor-events)
|
|
149
|
-
or [how to use proxies](https://docs.apify.com/sdk/python/docs/concepts/proxy-management).
|
apify-1.7.1b1.dist-info/RECORD
DELETED
|
@@ -1,41 +0,0 @@
|
|
|
1
|
-
apify/__init__.py,sha256=aAjho-r0-XAqUjD9j55ueCo4lZJzyytOWjk0VCmkeeY,283
|
|
2
|
-
apify/_crypto.py,sha256=mbqwfgVz7efAw6ko1PTtpaaRqlBvTi-oskiZmWufTrk,5822
|
|
3
|
-
apify/_utils.py,sha256=7_iHGRw8AZA7ITStg5cN8k_ZmqMKdAQ_ev2ZRcO3X0M,16963
|
|
4
|
-
apify/actor.py,sha256=v_hefwMXy2qCIBjcZvVHE9zdHg2jut0Xuf6IodX_vvo,59997
|
|
5
|
-
apify/config.py,sha256=mPbTqKe09hJXXGqKLuNRXGdBNod9mn1ACujRSm80GRQ,8785
|
|
6
|
-
apify/consts.py,sha256=eSD23HmwLKwWG8bRp5O1c7bmtlhvYE17Yw46BKs4vQQ,2263
|
|
7
|
-
apify/event_manager.py,sha256=k4_f977esIOvgGshec4yUSulU10-UsEkoVEV4sZEjwg,10612
|
|
8
|
-
apify/log.py,sha256=PObD-34j4GFUTLHHWDfgdd39ftfERBQBTc2DyvPJT3o,5005
|
|
9
|
-
apify/proxy_configuration.py,sha256=ZMNZHj0EQDPuXKdjcVP3eXazCRYUkmYR6hUlVyonUhk,15735
|
|
10
|
-
apify/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
11
|
-
apify/_memory_storage/__init__.py,sha256=frNb9kh6bfKtZNEMe2PA_QlT6DTUbhffcNfWhELiZNQ,90
|
|
12
|
-
apify/_memory_storage/file_storage_utils.py,sha256=83gd8ruzY_vkrpHT1ZeG3r8qJJKCKLeuGrxsBQgXeAE,2266
|
|
13
|
-
apify/_memory_storage/memory_storage_client.py,sha256=5v6tUjzFIW7Mpr4iK0tERysRwgTt5TeEDoyjqTXjf-o,10598
|
|
14
|
-
apify/_memory_storage/resource_clients/__init__.py,sha256=afkbzv59lgBe_JCgJcTbAt-ayX0VjtO6u0ExI7JVkEk,705
|
|
15
|
-
apify/_memory_storage/resource_clients/base_resource_client.py,sha256=YbjqNvRU34mBw3zVyGVN60k5Me4Koq1D2hFHF3oUBYA,5163
|
|
16
|
-
apify/_memory_storage/resource_clients/base_resource_collection_client.py,sha256=et-ChUnuLPnk_dYXG9kyPsvY9seM-5WIjYfGC5cMDeo,3986
|
|
17
|
-
apify/_memory_storage/resource_clients/dataset.py,sha256=ySPzEQXeopwKLNhlEGvYl9KvuGz5u86piHWT2xDns6w,20062
|
|
18
|
-
apify/_memory_storage/resource_clients/dataset_collection.py,sha256=tk5GUb1azeHQwFuX106AhGt7I_1sHWSV2n952-p4rug,1614
|
|
19
|
-
apify/_memory_storage/resource_clients/key_value_store.py,sha256=5LVTuSzsSS6uDmUXAKa1ShyFRsES3eDDpguVGDb-OkE,20581
|
|
20
|
-
apify/_memory_storage/resource_clients/key_value_store_collection.py,sha256=CBTcgffPmxLdEWz3KfjNsrQO49NHwW3QOD-AYA_C5hU,1740
|
|
21
|
-
apify/_memory_storage/resource_clients/request_queue.py,sha256=6skV2fGpDxrDtn43oQIiBxd4kA5wJ8ygw7_Yy1q7M_M,19700
|
|
22
|
-
apify/_memory_storage/resource_clients/request_queue_collection.py,sha256=qW7kPLKRl5mukIGCT8iNCsXT82BUYSwCV_KH7MLj528,1713
|
|
23
|
-
apify/scrapy/__init__.py,sha256=xrhyVgPvdB_kB6ugkhUM4YM3WkvBUu5ZiV_4bW11LwM,195
|
|
24
|
-
apify/scrapy/requests.py,sha256=BBjXUametZNVgV-BzTLnrv3rOIxBnAtCkakkCf7ZFvs,7935
|
|
25
|
-
apify/scrapy/scheduler.py,sha256=51GME-shm0-Yks2ERmIJRrCCJ6oCId5757obQmbCNTY,5789
|
|
26
|
-
apify/scrapy/utils.py,sha256=A_BhU_yxPQ__SYsoz9dMiwJ2pbh-oZCuEwVMKaSXtwo,3899
|
|
27
|
-
apify/scrapy/middlewares/__init__.py,sha256=gb3bCu__5wKO_ePhfFgGm-Chw384r8IbC3eoIsz0uG0,50
|
|
28
|
-
apify/scrapy/middlewares/apify_proxy.py,sha256=pDNx31y7llSv3ZM1SSujEYZSWQTfNfAqKvsNph5zbbU,5919
|
|
29
|
-
apify/scrapy/pipelines/__init__.py,sha256=KBUE3maOWrLfJRmWSsyW6YxxZY4lCGP2GZyMm9Z56VY,57
|
|
30
|
-
apify/scrapy/pipelines/actor_dataset_push.py,sha256=SlddL0Cwu32lQ6jYPsXybsrjHlrh7N-ADaH4a8ni4Do,959
|
|
31
|
-
apify/storages/__init__.py,sha256=rBdwhyZxUMG6m_7uAb4sl5eg_dxiLvYVas5aRcZ6PIE,268
|
|
32
|
-
apify/storages/base_storage.py,sha256=exPzjyMkkUccvg2qPcjZtLJQLWhfrlQxQHV-8p_K8w0,7434
|
|
33
|
-
apify/storages/dataset.py,sha256=gfMlJ6dSXDdjCykkStZCyp4u8xKCIZqflGS9-jLzK74,23339
|
|
34
|
-
apify/storages/key_value_store.py,sha256=BUGYPI4MuRlOJ_aPzZr8bq7ay_K04qAZ7yKW7C8ItV4,10760
|
|
35
|
-
apify/storages/request_queue.py,sha256=68pM2nJUYjkdpBTM315NnjRYE_yzeoslVtBQRB7bm74,28829
|
|
36
|
-
apify/storages/storage_client_manager.py,sha256=fvXg3PRojATNamEN29BBZyZZ5GWN_s0r29A59aiL-wQ,2465
|
|
37
|
-
apify-1.7.1b1.dist-info/LICENSE,sha256=AsFjHssKjj4LGd2ZCqXn6FBzMqcWdjQre1byPPSypVw,11355
|
|
38
|
-
apify-1.7.1b1.dist-info/METADATA,sha256=Y55ixx0bj7gvQA-i6piqzgXHgLWvnxrK2KRAyXWTDWw,6236
|
|
39
|
-
apify-1.7.1b1.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
|
|
40
|
-
apify-1.7.1b1.dist-info/top_level.txt,sha256=2oFNsHggn5m_rCaaP7xijQg_-Va2ByOSYuvKgACsS5w,6
|
|
41
|
-
apify-1.7.1b1.dist-info/RECORD,,
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
apify
|
|
File without changes
|