File size: 2,097 Bytes
ba2ab69
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""Web scraping commands using Playwright"""
from __future__ import annotations

try:
    from playwright.sync_api import sync_playwright
except ImportError:
    print(
        "Playwright not installed. Please install it with 'pip install playwright' to use."
    )
from bs4 import BeautifulSoup

from autogpt.processing.html import extract_hyperlinks, format_hyperlinks


def scrape_text(url: str) -> str:
    """Scrape text from a webpage

    Args:
        url (str): The URL to scrape text from

    Returns:
        str: The scraped text
    """
    with sync_playwright() as p:
        browser = p.chromium.launch()
        page = browser.new_page()

        try:
            page.goto(url)
            html_content = page.content()
            soup = BeautifulSoup(html_content, "html.parser")

            for script in soup(["script", "style"]):
                script.extract()

            text = soup.get_text()
            lines = (line.strip() for line in text.splitlines())
            chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
            text = "\n".join(chunk for chunk in chunks if chunk)

        except Exception as e:
            text = f"Error: {str(e)}"

        finally:
            browser.close()

    return text


def scrape_links(url: str) -> str | list[str]:
    """Scrape links from a webpage

    Args:
        url (str): The URL to scrape links from

    Returns:
        Union[str, List[str]]: The scraped links
    """
    with sync_playwright() as p:
        browser = p.chromium.launch()
        page = browser.new_page()

        try:
            page.goto(url)
            html_content = page.content()
            soup = BeautifulSoup(html_content, "html.parser")

            for script in soup(["script", "style"]):
                script.extract()

            hyperlinks = extract_hyperlinks(soup, url)
            formatted_links = format_hyperlinks(hyperlinks)

        except Exception as e:
            formatted_links = f"Error: {str(e)}"

        finally:
            browser.close()

    return formatted_links