swarmauri_tool_webscraping 0.7.0.dev12__tar.gz → 0.7.1.dev1__tar.gz
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.
- swarmauri_tool_webscraping-0.7.1.dev1/PKG-INFO +71 -0
- swarmauri_tool_webscraping-0.7.1.dev1/README.md +52 -0
- {swarmauri_tool_webscraping-0.7.0.dev12 → swarmauri_tool_webscraping-0.7.1.dev1}/pyproject.toml +2 -2
- swarmauri_tool_webscraping-0.7.0.dev12/PKG-INFO +0 -66
- swarmauri_tool_webscraping-0.7.0.dev12/README.md +0 -47
- {swarmauri_tool_webscraping-0.7.0.dev12 → swarmauri_tool_webscraping-0.7.1.dev1}/LICENSE +0 -0
- {swarmauri_tool_webscraping-0.7.0.dev12 → swarmauri_tool_webscraping-0.7.1.dev1}/swarmauri_tool_webscraping/WebScrapingTool.py +0 -0
- {swarmauri_tool_webscraping-0.7.0.dev12 → swarmauri_tool_webscraping-0.7.1.dev1}/swarmauri_tool_webscraping/__init__.py +0 -0
|
@@ -0,0 +1,71 @@
|
|
|
1
|
+
Metadata-Version: 2.3
|
|
2
|
+
Name: swarmauri_tool_webscraping
|
|
3
|
+
Version: 0.7.1.dev1
|
|
4
|
+
Summary: Web Scraping Tool for Swarmauri
|
|
5
|
+
License: Apache-2.0
|
|
6
|
+
Author: Jacob Stewart
|
|
7
|
+
Author-email: jacob@swarmauri.com
|
|
8
|
+
Requires-Python: >=3.10,<3.13
|
|
9
|
+
Classifier: License :: OSI Approved :: Apache Software License
|
|
10
|
+
Classifier: Programming Language :: Python :: 3.10
|
|
11
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
12
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
13
|
+
Requires-Dist: beautifulsoup4 (>=4.10.0)
|
|
14
|
+
Requires-Dist: swarmauri_base
|
|
15
|
+
Requires-Dist: swarmauri_core
|
|
16
|
+
Requires-Dist: swarmauri_standard
|
|
17
|
+
Description-Content-Type: text/markdown
|
|
18
|
+
|
|
19
|
+
|
|
20
|
+
|
|
21
|
+
|
|
22
|
+
<p align="center">
|
|
23
|
+
<a href="https://pypi.org/project/swarmauri_tool_webscraping/">
|
|
24
|
+
<img src="https://img.shields.io/pypi/dm/swarmauri_tool_webscraping" alt="PyPI - Downloads"/></a>
|
|
25
|
+
<a href="https://github.com/swarmauri/swarmauri-sdk/blob/master/pkgs/community/swarmauri_tool_webscraping/README.md">
|
|
26
|
+
<img src="https://hits.seeyoufarm.com/api/count/incr/badge.svg?url=https://github.com/swarmauri/swarmauri-sdk/pkgs/community/swarmauri_tool_webscraping/README.md&count_bg=%2379C83D&title_bg=%23555555&icon=&icon_color=%23E7E7E7&title=hits&edge_flat=false" alt="GitHub Hits"/></a>
|
|
27
|
+
<a href="https://pypi.org/project/swarmauri_tool_webscraping/">
|
|
28
|
+
<img src="https://img.shields.io/pypi/pyversions/swarmauri_tool_webscraping" alt="PyPI - Python Version"/></a>
|
|
29
|
+
<a href="https://pypi.org/project/swarmauri_tool_webscraping/">
|
|
30
|
+
<img src="https://img.shields.io/pypi/l/swarmauri_tool_webscraping" alt="PyPI - License"/></a>
|
|
31
|
+
<a href="https://pypi.org/project/swarmauri_tool_webscraping/">
|
|
32
|
+
<img src="https://img.shields.io/pypi/v/swarmauri_tool_webscraping?label=swarmauri_tool_webscraping&color=green" alt="PyPI - swarmauri_tool_webscraping"/></a>
|
|
33
|
+
</p>
|
|
34
|
+
|
|
35
|
+
---
|
|
36
|
+
|
|
37
|
+
# Swarmauri Tool Web Scraping
|
|
38
|
+
|
|
39
|
+
A web scraping tool that uses Python's requests and BeautifulSoup libraries to parse web content using CSS selectors.
|
|
40
|
+
|
|
41
|
+
## Installation
|
|
42
|
+
|
|
43
|
+
```bash
|
|
44
|
+
pip install swarmauri_tool_webscraping
|
|
45
|
+
```
|
|
46
|
+
|
|
47
|
+
## Usage
|
|
48
|
+
|
|
49
|
+
```python
|
|
50
|
+
from swarmauri.tools.WebScrapingTool import WebScrapingTool
|
|
51
|
+
|
|
52
|
+
# Initialize the tool
|
|
53
|
+
scraper = WebScrapingTool()
|
|
54
|
+
|
|
55
|
+
# Scrape content from a webpage
|
|
56
|
+
result = scraper(
|
|
57
|
+
url="https://example.com",
|
|
58
|
+
selector="h1"
|
|
59
|
+
)
|
|
60
|
+
|
|
61
|
+
# Access the extracted text
|
|
62
|
+
if "extracted_text" in result:
|
|
63
|
+
print(result["extracted_text"])
|
|
64
|
+
else:
|
|
65
|
+
print(result["error"])
|
|
66
|
+
```
|
|
67
|
+
|
|
68
|
+
## Want to help?
|
|
69
|
+
|
|
70
|
+
If you want to contribute to swarmauri-sdk, read up on our [guidelines for contributing](https://github.com/swarmauri/swarmauri-sdk/blob/master/contributing.md) that will help you get started.
|
|
71
|
+
|
|
@@ -0,0 +1,52 @@
|
|
|
1
|
+
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
<p align="center">
|
|
5
|
+
<a href="https://pypi.org/project/swarmauri_tool_webscraping/">
|
|
6
|
+
<img src="https://img.shields.io/pypi/dm/swarmauri_tool_webscraping" alt="PyPI - Downloads"/></a>
|
|
7
|
+
<a href="https://github.com/swarmauri/swarmauri-sdk/blob/master/pkgs/community/swarmauri_tool_webscraping/README.md">
|
|
8
|
+
<img src="https://hits.seeyoufarm.com/api/count/incr/badge.svg?url=https://github.com/swarmauri/swarmauri-sdk/pkgs/community/swarmauri_tool_webscraping/README.md&count_bg=%2379C83D&title_bg=%23555555&icon=&icon_color=%23E7E7E7&title=hits&edge_flat=false" alt="GitHub Hits"/></a>
|
|
9
|
+
<a href="https://pypi.org/project/swarmauri_tool_webscraping/">
|
|
10
|
+
<img src="https://img.shields.io/pypi/pyversions/swarmauri_tool_webscraping" alt="PyPI - Python Version"/></a>
|
|
11
|
+
<a href="https://pypi.org/project/swarmauri_tool_webscraping/">
|
|
12
|
+
<img src="https://img.shields.io/pypi/l/swarmauri_tool_webscraping" alt="PyPI - License"/></a>
|
|
13
|
+
<a href="https://pypi.org/project/swarmauri_tool_webscraping/">
|
|
14
|
+
<img src="https://img.shields.io/pypi/v/swarmauri_tool_webscraping?label=swarmauri_tool_webscraping&color=green" alt="PyPI - swarmauri_tool_webscraping"/></a>
|
|
15
|
+
</p>
|
|
16
|
+
|
|
17
|
+
---
|
|
18
|
+
|
|
19
|
+
# Swarmauri Tool Web Scraping
|
|
20
|
+
|
|
21
|
+
A web scraping tool that uses Python's requests and BeautifulSoup libraries to parse web content using CSS selectors.
|
|
22
|
+
|
|
23
|
+
## Installation
|
|
24
|
+
|
|
25
|
+
```bash
|
|
26
|
+
pip install swarmauri_tool_webscraping
|
|
27
|
+
```
|
|
28
|
+
|
|
29
|
+
## Usage
|
|
30
|
+
|
|
31
|
+
```python
|
|
32
|
+
from swarmauri.tools.WebScrapingTool import WebScrapingTool
|
|
33
|
+
|
|
34
|
+
# Initialize the tool
|
|
35
|
+
scraper = WebScrapingTool()
|
|
36
|
+
|
|
37
|
+
# Scrape content from a webpage
|
|
38
|
+
result = scraper(
|
|
39
|
+
url="https://example.com",
|
|
40
|
+
selector="h1"
|
|
41
|
+
)
|
|
42
|
+
|
|
43
|
+
# Access the extracted text
|
|
44
|
+
if "extracted_text" in result:
|
|
45
|
+
print(result["extracted_text"])
|
|
46
|
+
else:
|
|
47
|
+
print(result["error"])
|
|
48
|
+
```
|
|
49
|
+
|
|
50
|
+
## Want to help?
|
|
51
|
+
|
|
52
|
+
If you want to contribute to swarmauri-sdk, read up on our [guidelines for contributing](https://github.com/swarmauri/swarmauri-sdk/blob/master/contributing.md) that will help you get started.
|
{swarmauri_tool_webscraping-0.7.0.dev12 → swarmauri_tool_webscraping-0.7.1.dev1}/pyproject.toml
RENAMED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
[project]
|
|
2
2
|
name = "swarmauri_tool_webscraping"
|
|
3
|
-
version = "0.7.
|
|
3
|
+
version = "0.7.1.dev1"
|
|
4
4
|
description = "Web Scraping Tool for Swarmauri"
|
|
5
5
|
license = "Apache-2.0"
|
|
6
6
|
readme = "README.md"
|
|
@@ -44,7 +44,7 @@ log_cli_format = "%(asctime)s [%(levelname)s] %(message)s"
|
|
|
44
44
|
log_cli_date_format = "%Y-%m-%d %H:%M:%S"
|
|
45
45
|
asyncio_default_fixture_loop_scope = "function"
|
|
46
46
|
|
|
47
|
-
[
|
|
47
|
+
[project.entry-points.'swarmauri.tools']
|
|
48
48
|
WebScrapingTool = "swarmauri_tool_webscraping.WebScrapingTool:WebScrapingTool"
|
|
49
49
|
[build-system]
|
|
50
50
|
requires = ["poetry-core>=1.0.0"]
|
|
@@ -1,66 +0,0 @@
|
|
|
1
|
-
Metadata-Version: 2.3
|
|
2
|
-
Name: swarmauri_tool_webscraping
|
|
3
|
-
Version: 0.7.0.dev12
|
|
4
|
-
Summary: Web Scraping Tool for Swarmauri
|
|
5
|
-
License: Apache-2.0
|
|
6
|
-
Author: Jacob Stewart
|
|
7
|
-
Author-email: jacob@swarmauri.com
|
|
8
|
-
Requires-Python: >=3.10,<3.13
|
|
9
|
-
Classifier: License :: OSI Approved :: Apache Software License
|
|
10
|
-
Classifier: Programming Language :: Python :: 3.10
|
|
11
|
-
Classifier: Programming Language :: Python :: 3.11
|
|
12
|
-
Classifier: Programming Language :: Python :: 3.12
|
|
13
|
-
Requires-Dist: beautifulsoup4 (>=4.10.0)
|
|
14
|
-
Requires-Dist: swarmauri_base
|
|
15
|
-
Requires-Dist: swarmauri_core
|
|
16
|
-
Requires-Dist: swarmauri_standard
|
|
17
|
-
Description-Content-Type: text/markdown
|
|
18
|
-
|
|
19
|
-
|
|
20
|
-
|
|
21
|
-
<div align="center">
|
|
22
|
-
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
|
|
26
|
-
|
|
27
|
-
|
|
28
|
-
</div>
|
|
29
|
-
|
|
30
|
-
---
|
|
31
|
-
|
|
32
|
-
# Web Scraping Tool
|
|
33
|
-
|
|
34
|
-
A web scraping tool that uses Python's requests and BeautifulSoup libraries to parse web content using CSS selectors.
|
|
35
|
-
|
|
36
|
-
## Installation
|
|
37
|
-
|
|
38
|
-
```bash
|
|
39
|
-
pip install swarmauri_tool_webscraping
|
|
40
|
-
```
|
|
41
|
-
|
|
42
|
-
## Usage
|
|
43
|
-
|
|
44
|
-
```python
|
|
45
|
-
from swarmauri.tools.WebScrapingTool import WebScrapingTool
|
|
46
|
-
|
|
47
|
-
# Initialize the tool
|
|
48
|
-
scraper = WebScrapingTool()
|
|
49
|
-
|
|
50
|
-
# Scrape content from a webpage
|
|
51
|
-
result = scraper(
|
|
52
|
-
url="https://example.com",
|
|
53
|
-
selector="h1"
|
|
54
|
-
)
|
|
55
|
-
|
|
56
|
-
# Access the extracted text
|
|
57
|
-
if "extracted_text" in result:
|
|
58
|
-
print(result["extracted_text"])
|
|
59
|
-
else:
|
|
60
|
-
print(result["error"])
|
|
61
|
-
```
|
|
62
|
-
|
|
63
|
-
## Want to help?
|
|
64
|
-
|
|
65
|
-
If you want to contribute to swarmauri-sdk, read up on our [guidelines for contributing](https://github.com/swarmauri/swarmauri-sdk/blob/master/contributing.md) that will help you get started.
|
|
66
|
-
|
|
@@ -1,47 +0,0 @@
|
|
|
1
|
-
|
|
2
|
-
|
|
3
|
-
<div align="center">
|
|
4
|
-
|
|
5
|
-
|
|
6
|
-
|
|
7
|
-
|
|
8
|
-
|
|
9
|
-
|
|
10
|
-
</div>
|
|
11
|
-
|
|
12
|
-
---
|
|
13
|
-
|
|
14
|
-
# Web Scraping Tool
|
|
15
|
-
|
|
16
|
-
A web scraping tool that uses Python's requests and BeautifulSoup libraries to parse web content using CSS selectors.
|
|
17
|
-
|
|
18
|
-
## Installation
|
|
19
|
-
|
|
20
|
-
```bash
|
|
21
|
-
pip install swarmauri_tool_webscraping
|
|
22
|
-
```
|
|
23
|
-
|
|
24
|
-
## Usage
|
|
25
|
-
|
|
26
|
-
```python
|
|
27
|
-
from swarmauri.tools.WebScrapingTool import WebScrapingTool
|
|
28
|
-
|
|
29
|
-
# Initialize the tool
|
|
30
|
-
scraper = WebScrapingTool()
|
|
31
|
-
|
|
32
|
-
# Scrape content from a webpage
|
|
33
|
-
result = scraper(
|
|
34
|
-
url="https://example.com",
|
|
35
|
-
selector="h1"
|
|
36
|
-
)
|
|
37
|
-
|
|
38
|
-
# Access the extracted text
|
|
39
|
-
if "extracted_text" in result:
|
|
40
|
-
print(result["extracted_text"])
|
|
41
|
-
else:
|
|
42
|
-
print(result["error"])
|
|
43
|
-
```
|
|
44
|
-
|
|
45
|
-
## Want to help?
|
|
46
|
-
|
|
47
|
-
If you want to contribute to swarmauri-sdk, read up on our [guidelines for contributing](https://github.com/swarmauri/swarmauri-sdk/blob/master/contributing.md) that will help you get started.
|
|
File without changes
|
|
File without changes
|