zhang_crawl_bio/get_article_info.py

import asyncio
from crawl4ai import *
from pathlib import Path
import json
output_dir = Path("output")

# 读取output\links.json  "external" 键值，得到列表
def read_links_from_json(file_path):
    with open(file_path, 'r', encoding='utf-8') as file:
        data = json.load(file,)
        links = data.get("external", [])
        return links
# 筛选列表中键 "base_domain" 的值不含有 google
def filter_links(links):
    filtered_links = [link for link in links if "google" not in link["base_domain"]]
    return filtered_links

def get_rearch_result_links(file_path):
    links = read_links_from_json(file_path)
    filtered_links = filter_links(links)
    return filtered_links

def main():
    filtered_links = get_rearch_result_links("output/links.json")
    print(filtered_links)
    print(len(filtered_links))

if __name__ == "__main__":
    main()