{
"event": "PreToolUse",
"tool_name": "Read",
"tool_input": {
"file_path": "\/var\/www\/dev.campus.systemische-tools.de\/crawler\/src\/infrastructure\/parsers\/html_parser_bs4.py",
"offset": 20,
"limit": 25
}
}
{
"tool_response": {
"type": "text",
"file": {
"filePath": "\/var\/www\/dev.campus.systemische-tools.de\/crawler\/src\/infrastructure\/parsers\/html_parser_bs4.py",
"content": "class Bs4HtmlParser(HtmlParserPort):\n def parse(self, html: str, *, base_url: str) -> ParsedDocument:\n soup = BeautifulSoup(html, \"lxml\")\n head = _parse_head(soup)\n og = _parse_og(soup)\n twitter = _parse_twitter(soup)\n body = _parse_body(soup)\n hreflang = _parse_hreflang(soup)\n internal, external = _parse_links(soup, base_url=base_url)\n images = _parse_images(soup, base_url=base_url)\n return ParsedDocument(\n head=head,\n og=og,\n twitter=twitter,\n body=body,\n hreflang=hreflang,\n internal_links=internal,\n external_links=external,\n image_specs=images,\n )\n\n\ndef _meta(soup: BeautifulSoup, name: str) -> str | None:\n tag = soup.find(\"meta\", attrs={\"name\": name})\n return _content(tag)",
"numLines": 25,
"startLine": 20,
"totalLines": 205
}
}
}