You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/libs/community/langchain_community/document_loaders/browserless.py

64 lines
2.0 KiB
Python

community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463) Moved the following modules to new package langchain-community in a backwards compatible fashion: ``` mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community ``` Moved the following to core ``` mv langchain/langchain/utils/json_schema.py core/langchain_core/utils mv langchain/langchain/utils/html.py core/langchain_core/utils mv langchain/langchain/utils/strings.py core/langchain_core/utils cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py rm langchain/langchain/utils/env.py ``` See .scripts/community_split/script_integrations.sh for all changes
7 months ago
from typing import Iterator, List, Union
import requests
from langchain_core.documents import Document
from langchain_community.document_loaders.base import BaseLoader
class BrowserlessLoader(BaseLoader):
"""Load webpages with `Browserless` /content endpoint."""
def __init__(
self, api_token: str, urls: Union[str, List[str]], text_content: bool = True
):
"""Initialize with API token and the URLs to scrape"""
self.api_token = api_token
"""Browserless API token."""
self.urls = urls
"""List of URLs to scrape."""
self.text_content = text_content
def lazy_load(self) -> Iterator[Document]:
"""Lazy load Documents from URLs."""
for url in self.urls:
if self.text_content:
response = requests.post(
"https://chrome.browserless.io/scrape",
params={
"token": self.api_token,
},
json={
"url": url,
"elements": [
{
"selector": "body",
}
],
},
)
yield Document(
page_content=response.json()["data"][0]["results"][0]["text"],
metadata={
"source": url,
},
)
else:
response = requests.post(
"https://chrome.browserless.io/content",
params={
"token": self.api_token,
},
json={
"url": url,
},
)
yield Document(
page_content=response.text,
metadata={
"source": url,
},
)