55 lines
2.0 KiB
Python
55 lines
2.0 KiB
Python
import os
|
||
import requests
|
||
import xml.etree.ElementTree as ET
|
||
import xmltodict
|
||
import json
|
||
|
||
# 测试用爬虫请求头
|
||
headers = {
|
||
"Content-Type": "application/atom+xml; charset=utf-8",
|
||
"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/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
|
||
"Accept-Language": "zh-CN,zh;q=0.9"
|
||
}
|
||
|
||
def fetch_rss(url, headers):
|
||
response = requests.get(url, headers=headers)
|
||
response.raise_for_status() # 检查请求是否成功
|
||
# print(response.content.decode('utf-8')) # 打印响应内容，确保获取的数据是正确的 XML 格式
|
||
return response.content
|
||
|
||
# 先知社区 爬虫
|
||
def xianzhi_main():
|
||
url = "https://xz.aliyun.com/feed"
|
||
rss_content = fetch_rss(url, headers)
|
||
# 将 XML 数据转换为 Python 字典
|
||
data = xmltodict.parse(rss_content)
|
||
|
||
# 提取所有的 <entry> 元素
|
||
entries = data['feed']['entry']
|
||
|
||
# 创建一个空列表来存储每个 <entry> 的 JSON 数据
|
||
entries_json = []
|
||
|
||
# 遍历每个 <entry> 元素，提取信息，并添加到列表中
|
||
for entry in entries:
|
||
entry_dict = {
|
||
'title': entry.get('title', ''),
|
||
'link': entry.get('link', {}).get('@href', ''), # 提取链接
|
||
'published': entry.get('published', ''),
|
||
'id': entry.get('id', ''),
|
||
'summary': entry.get('summary', '')
|
||
}
|
||
entries_json.append(entry_dict)
|
||
|
||
# 将 <entry> 元素的列表转换为 JSON 格式
|
||
json_data = json.dumps(entries_json, ensure_ascii=False, indent=4)
|
||
|
||
# 保存 JSON 数据到文件
|
||
with open('./JSON/xianzhi.json', 'w', encoding='utf-8') as json_file:
|
||
json_file.write(json_data)
|
||
|
||
print("数据已保存到./JSON/xianzhi.json！")
|