This repository has been archived by the owner on Jan 31, 2025. It is now read-only.
forked from Significant-Gravitas/AutoGPT
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtest_browse_scrape_text.py
117 lines (95 loc) · 4.85 KB
/
test_browse_scrape_text.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
# Generated by CodiumAI
import pytest
import requests
from autogpt.agent.agent import Agent
from autogpt.commands.web_requests import scrape_text
"""
Code Analysis
Objective:
The objective of the "scrape_text" function is to scrape the text content from
a given URL and return it as a string, after removing any unwanted HTML tags and
scripts.
Inputs:
- url: a string representing the URL of the webpage to be scraped.
Flow:
1. Send a GET request to the given URL using the requests library and the user agent
header from the config file.
2. Check if the response contains an HTTP error. If it does, return an error message.
3. Use BeautifulSoup to parse the HTML content of the response and extract all script
and style tags.
4. Get the text content of the remaining HTML using the get_text() method of
BeautifulSoup.
5. Split the text into lines and then into chunks, removing any extra whitespace.
6. Join the chunks into a single string with newline characters between them.
7. Return the cleaned text.
Outputs:
- A string representing the cleaned text content of the webpage.
Additional aspects:
- The function uses the requests library and BeautifulSoup to handle the HTTP request
and HTML parsing, respectively.
- The function removes script and style tags from the HTML to avoid including unwanted
content in the text output.
- The function uses a generator expression to split the text into lines and chunks,
which can improve performance for large amounts of text.
"""
class TestScrapeText:
def test_scrape_text_with_valid_url(self, mocker, agent: Agent):
"""Tests that scrape_text() returns the expected text when given a valid URL."""
# Mock the requests.get() method to return a response with expected text
expected_text = "This is some sample text"
mock_response = mocker.Mock()
mock_response.status_code = 200
mock_response.text = (
"<html><body><div><p style='color: blue;'>"
f"{expected_text}</p></div></body></html>"
)
mocker.patch("requests.Session.get", return_value=mock_response)
# Call the function with a valid URL and assert that it returns the
# expected text
url = "http://www.example.com"
assert scrape_text(url, agent) == expected_text
def test_invalid_url(self, agent: Agent):
"""Tests that an error is raised when an invalid url is provided."""
url = "invalidurl.com"
pytest.raises(ValueError, scrape_text, url, agent)
def test_unreachable_url(self, mocker, agent: Agent):
"""Test that scrape_text returns an error message when an invalid or unreachable url is provided."""
# Mock the requests.get() method to raise an exception
mocker.patch(
"requests.Session.get", side_effect=requests.exceptions.RequestException
)
# Call the function with an invalid URL and assert that it returns an error
# message
url = "http://thiswebsitedoesnotexist.net/"
error_message = scrape_text(url, agent)
assert "Error:" in error_message
def test_no_text(self, mocker, agent: Agent):
"""Test that scrape_text returns an empty string when the html page contains no text to be scraped."""
# Mock the requests.get() method to return a response with no text
mock_response = mocker.Mock()
mock_response.status_code = 200
mock_response.text = "<html><body></body></html>"
mocker.patch("requests.Session.get", return_value=mock_response)
# Call the function with a valid URL and assert that it returns an empty string
url = "http://www.example.com"
assert scrape_text(url, agent) == ""
def test_http_error(self, mocker, agent: Agent):
"""Test that scrape_text returns an error message when the response status code is an http error (>=400)."""
# Mock the requests.get() method to return a response with a 404 status code
mocker.patch("requests.Session.get", return_value=mocker.Mock(status_code=404))
# Call the function with a URL
result = scrape_text("https://www.example.com", agent)
# Check that the function returns an error message
assert result == "Error: HTTP 404 error"
def test_scrape_text_with_html_tags(self, mocker, agent: Agent):
"""Test that scrape_text() properly handles HTML tags."""
# Create a mock response object with HTML containing tags
html = "<html><body><p>This is <b>bold</b> text.</p></body></html>"
mock_response = mocker.Mock()
mock_response.status_code = 200
mock_response.text = html
mocker.patch("requests.Session.get", return_value=mock_response)
# Call the function with a URL
result = scrape_text("https://www.example.com", agent)
# Check that the function properly handles HTML tags
assert result == "This is bold text."