mirror of
https://github.com/QuivrHQ/quivr.git
synced 2024-12-15 17:43:03 +03:00
51 lines
1.2 KiB
Python
51 lines
1.2 KiB
Python
import os
|
|
import re
|
|
import tempfile
|
|
import unicodedata
|
|
|
|
import requests
|
|
from pydantic import BaseModel
|
|
|
|
|
|
class CrawlWebsite(BaseModel):
|
|
url: str
|
|
js: bool = False
|
|
depth: int = 1
|
|
max_pages: int = 100
|
|
max_time: int = 60
|
|
|
|
def _crawl(self, url):
|
|
response = requests.get(url)
|
|
if response.status_code == 200:
|
|
return response.text
|
|
else:
|
|
return None
|
|
|
|
def process(self):
|
|
content = self._crawl(self.url)
|
|
|
|
# Create a file
|
|
file_name = slugify(self.url) + ".html"
|
|
temp_file_path = os.path.join(tempfile.gettempdir(), file_name)
|
|
with open(temp_file_path, "w") as temp_file:
|
|
temp_file.write(content) # pyright: ignore reportPrivateUsage=none
|
|
# Process the file
|
|
|
|
if content:
|
|
return temp_file_path, file_name
|
|
else:
|
|
return None
|
|
|
|
def checkGithub(self):
|
|
if "github.com" in self.url:
|
|
return True
|
|
else:
|
|
return False
|
|
|
|
|
|
def slugify(text):
|
|
text = unicodedata.normalize("NFKD", text).encode("ascii", "ignore").decode("utf-8")
|
|
text = re.sub(r"[^\w\s-]", "", text).strip().lower()
|
|
text = re.sub(r"[-\s]+", "-", text)
|
|
return text
|