83 lines
2.9 KiB
Python
83 lines
2.9 KiB
Python
# -*- coding: utf-8 -*-
|
||
import os
|
||
import requests
|
||
import xml.etree.ElementTree as ET
|
||
import json
|
||
from requests.exceptions import RequestException
|
||
from loguru import logger
|
||
|
||
logger.add("./log/spider.log",
|
||
format="{time:YYYY-MM-DD HH:mm:ss} - {level} - {name}:{function}:{line} - {message}",
|
||
rotation="10 MB",
|
||
compression="zip",
|
||
encoding="utf-8")
|
||
# shell终端打印日志
|
||
# logger.add(lambda msg: print(msg),
|
||
# format="{time:YYYY-MM-DD HH:mm:ss} - {level} - {name}:{function}:{line} - {message}")
|
||
|
||
# 测试用爬虫请求头
|
||
headers = {
|
||
"Content-Type": "application/json",
|
||
"Cache-Control": "no-cache",
|
||
"Upgrade-Insecure-Requests": "1",
|
||
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.55 Safari/537.36",
|
||
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
|
||
"Sec-Fetch-Site": "same-origin",
|
||
"Sec-Fetch-Mode": "navigate",
|
||
"Sec-Fetch-User": "?1",
|
||
"Sec-Fetch-Dest": "document",
|
||
"Accept-Language": "zh-CN,zh;q=0.9"
|
||
}
|
||
|
||
def fetch_rss(url, headers, timeout=20):
|
||
try:
|
||
response = requests.get(url, headers=headers, timeout=timeout)
|
||
response.raise_for_status() # 检查请求是否成功
|
||
return response.content
|
||
except requests.Timeout:
|
||
logger.warning(f"请求 {url} 超时，跳过保存操作。")
|
||
return None
|
||
except RequestException as e:
|
||
logger.error(f"请求 {url} 时发生错误: {e}")
|
||
return None # 返回None表示请求失败
|
||
|
||
def parse_rss(rss_content):
|
||
items = []
|
||
root = ET.fromstring(rss_content)
|
||
for item in root.findall('.//item'):
|
||
item_dict = {}
|
||
for child in item:
|
||
tag = child.tag
|
||
# 将一标签替换名称方便处理
|
||
if tag.startswith('{http://purl.org/rss/1.0/modules/content/}'):
|
||
tag = 'body'
|
||
item_dict[tag] = child.text
|
||
items.append(item_dict)
|
||
return items
|
||
|
||
def save_to_json(data, filename):
|
||
with open(filename, 'w', encoding='utf-8') as f:
|
||
json.dump(data, f, ensure_ascii=False, indent=4)
|
||
|
||
def freebuf_main():
|
||
url = "https://www.freebuf.com/feed"
|
||
rss_content = fetch_rss(url, headers)
|
||
|
||
if rss_content is None:
|
||
logger.warning("无法获取Freebuf RSS内容，跳过保存操作。")
|
||
return
|
||
|
||
try:
|
||
items = parse_rss(rss_content)
|
||
|
||
# 确保目录存在
|
||
os.makedirs(os.path.dirname('./JSON/freebuf.json'), exist_ok=True)
|
||
|
||
# 将解析后的数据保存到 JSON 文件
|
||
save_to_json(items, './JSON/freebuf.json')
|
||
logger.info("数据已保存到 ./JSON/freebuf.json！")
|
||
except Exception as e:
|
||
logger.error(f"解析或保存Freebuf RSS内容时发生错误: {e}")
|
||
|
||
if __name__ == '__main__':
|
||
freebuf_main() |