Harrison/headers (#1696)

Co-authored-by: Tim Asp <707699+timothyasp@users.noreply.github.com>
This commit is contained in:
Harrison Chase 2023-03-15 13:13:21 -07:00 committed by GitHub
parent 3ea6d9c4d2
commit aad4bff098
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -1,24 +1,50 @@
"""Web base loader class."""
from typing import Any, List
import logging
from typing import Any, List, Optional
import requests
from langchain.docstore.document import Document
from langchain.document_loaders.base import BaseLoader
logger = logging.getLogger(__file__)
default_header_template = {
"User-Agent": "",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*"
";q=0.8",
"Accept-Language": "en-US,en;q=0.5",
"Referer": "https://www.google.com/",
"DNT": "1",
"Connection": "keep-alive",
"Upgrade-Insecure-Requests": "1",
}
class WebBaseLoader(BaseLoader):
"""Loader that uses urllib and beautiful soup to load webpages."""
def __init__(self, web_path: str):
def __init__(self, web_path: str, header_template: Optional[dict] = None):
"""Initialize with webpage path."""
self.web_path = web_path
self.session = requests.Session()
@staticmethod
def _scrape(url: str) -> Any:
try:
from fake_useragent import UserAgent
headers = header_template or default_header_template
headers["User-Agent"] = UserAgent().random
self.session.headers = dict(headers)
except ImportError:
logger.info(
"fake_useragent not found, using default user agent."
"To get a realistic header for requests, `pip install fake_useragent`."
)
def _scrape(self, url: str) -> Any:
from bs4 import BeautifulSoup
html_doc = requests.get(url)
html_doc = self.session.get(url)
soup = BeautifulSoup(html_doc.text, "html.parser")
return soup