mirror of
https://github.com/hwchase17/langchain.git
synced 2025-11-14 19:08:33 +00:00
a0c2281540
```python
"""python scripts/update_mypy_ruff.py"""
import glob
import tomllib
from pathlib import Path
import toml
import subprocess
import re
ROOT_DIR = Path(__file__).parents[1]
def main():
for path in glob.glob(str(ROOT_DIR / "libs/**/pyproject.toml"), recursive=True):
print(path)
with open(path, "rb") as f:
pyproject = tomllib.load(f)
try:
pyproject["tool"]["poetry"]["group"]["typing"]["dependencies"]["mypy"] = (
"^1.10"
)
pyproject["tool"]["poetry"]["group"]["lint"]["dependencies"]["ruff"] = (
"^0.5"
)
except KeyError:
continue
with open(path, "w") as f:
toml.dump(pyproject, f)
cwd = "/".join(path.split("/")[:-1])
completed = subprocess.run(
"poetry lock --no-update; poetry install --with typing; poetry run mypy . --no-color",
cwd=cwd,
shell=True,
capture_output=True,
text=True,
)
logs = completed.stdout.split("\n")
to_ignore = {}
for l in logs:
if re.match("^(.*)\:(\d+)\: error:.*\[(.*)\]", l):
path, line_no, error_type = re.match(
"^(.*)\:(\d+)\: error:.*\[(.*)\]", l
).groups()
if (path, line_no) in to_ignore:
to_ignore[(path, line_no)].append(error_type)
else:
to_ignore[(path, line_no)] = [error_type]
print(len(to_ignore))
for (error_path, line_no), error_types in to_ignore.items():
all_errors = ", ".join(error_types)
full_path = f"{cwd}/{error_path}"
try:
with open(full_path, "r") as f:
file_lines = f.readlines()
except FileNotFoundError:
continue
file_lines[int(line_no) - 1] = (
file_lines[int(line_no) - 1][:-1] + f" # type: ignore[{all_errors}]\n"
)
with open(full_path, "w") as f:
f.write("".join(file_lines))
subprocess.run(
"poetry run ruff format .; poetry run ruff --select I --fix .",
cwd=cwd,
shell=True,
capture_output=True,
text=True,
)
if __name__ == "__main__":
main()
```
71 lines
2.5 KiB
Python
71 lines
2.5 KiB
Python
"""Scrapfly Web Reader."""
|
|
|
|
import logging
|
|
from typing import Iterator, List, Literal, Optional
|
|
|
|
from langchain_core.document_loaders import BaseLoader
|
|
from langchain_core.documents import Document
|
|
from langchain_core.utils import get_from_env
|
|
|
|
logger = logging.getLogger(__file__)
|
|
|
|
|
|
class ScrapflyLoader(BaseLoader):
|
|
"""Turn a url to llm accessible markdown with `Scrapfly.io`.
|
|
|
|
For further details, visit: https://scrapfly.io/docs/sdk/python
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
urls: List[str],
|
|
*,
|
|
api_key: Optional[str] = None,
|
|
scrape_format: Literal["markdown", "text"] = "markdown",
|
|
scrape_config: Optional[dict] = None,
|
|
continue_on_failure: bool = True,
|
|
) -> None:
|
|
"""Initialize client.
|
|
|
|
Args:
|
|
urls: List of urls to scrape.
|
|
api_key: The Scrapfly API key. If not specified must have env var
|
|
SCRAPFLY_API_KEY set.
|
|
scrape_format: Scrape result format, one or "markdown" or "text".
|
|
scrape_config: Dictionary of ScrapFly scrape config object.
|
|
continue_on_failure: Whether to continue if scraping a url fails.
|
|
"""
|
|
try:
|
|
from scrapfly import ScrapflyClient
|
|
except ImportError:
|
|
raise ImportError(
|
|
"`scrapfly` package not found, please run `pip install scrapfly-sdk`"
|
|
)
|
|
if not urls:
|
|
raise ValueError("URLs must be provided.")
|
|
api_key = api_key or get_from_env("api_key", "SCRAPFLY_API_KEY")
|
|
self.scrapfly = ScrapflyClient(key=api_key)
|
|
self.urls = urls
|
|
self.scrape_format = scrape_format
|
|
self.scrape_config = scrape_config
|
|
self.continue_on_failure = continue_on_failure
|
|
|
|
def lazy_load(self) -> Iterator[Document]:
|
|
from scrapfly import ScrapeConfig
|
|
|
|
scrape_config = self.scrape_config if self.scrape_config is not None else {}
|
|
for url in self.urls:
|
|
try:
|
|
response = self.scrapfly.scrape(
|
|
ScrapeConfig(url, format=self.scrape_format, **scrape_config)
|
|
)
|
|
yield Document(
|
|
page_content=response.scrape_result["content"],
|
|
metadata={"url": url},
|
|
)
|
|
except Exception as e:
|
|
if self.continue_on_failure:
|
|
logger.error(f"Error fetching data from {url}, exception: {e}")
|
|
else:
|
|
raise e
|