Skip to content

Tool

WebScraper

Bases: BaseTool

Source code in griptape/griptape/tools/web_scraper/tool.py 
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
@define
class WebScraper(BaseTool):
    include_links: bool = field(default=True, kw_only=True)

    @activity(
        config={
            "description": "Can be used to browse a web page and load its content",
            "schema": Schema({Literal("url", description="Valid HTTP URL"): str}),
        }
    )
    def get_content(self, params: dict) -> ListArtifact | ErrorArtifact:
        url = params["values"]["url"]
        page = WebLoader().extract_page(url, self.include_links)

        if isinstance(page, ErrorArtifact):
            return page
        else:
            return ListArtifact(TextLoader().text_to_artifacts(page.get("text")))

    @activity(
        config={
            "description": "Can be used to load a web page author",
            "schema": Schema({Literal("url", description="Valid HTTP URL"): str}),
        }
    )
    def get_author(self, params: dict) -> BaseArtifact:
        url = params["values"]["url"]
        page = WebLoader().extract_page(url, self.include_links)

        if isinstance(page, ErrorArtifact):
            return page
        else:
            return TextArtifact(page.get("author"))

get_author(params)

Source code in griptape/griptape/tools/web_scraper/tool.py 
30
31
32
33
34
35
36
37
38
39
40
41
42
43
@activity(
    config={
        "description": "Can be used to load a web page author",
        "schema": Schema({Literal("url", description="Valid HTTP URL"): str}),
    }
)
def get_author(self, params: dict) -> BaseArtifact:
    url = params["values"]["url"]
    page = WebLoader().extract_page(url, self.include_links)

    if isinstance(page, ErrorArtifact):
        return page
    else:
        return TextArtifact(page.get("author"))

get_content(params)

Source code in griptape/griptape/tools/web_scraper/tool.py 
15
16
17
18
19
20
21
22
23
24
25
26
27
28
@activity(
    config={
        "description": "Can be used to browse a web page and load its content",
        "schema": Schema({Literal("url", description="Valid HTTP URL"): str}),
    }
)
def get_content(self, params: dict) -> ListArtifact | ErrorArtifact:
    url = params["values"]["url"]
    page = WebLoader().extract_page(url, self.include_links)

    if isinstance(page, ErrorArtifact):
        return page
    else:
        return ListArtifact(TextLoader().text_to_artifacts(page.get("text")))