爬取今日头条财经版块新闻

使用jupyter编辑, etree爬取

进入头条财经新闻网页,无法获取原网页内容,在查看各个请求中发现一个url里包含新闻信息.信息都在data里

 

import requests
from lxml import etree
import json

url = "https://www.toutiao.com/api/pc/feed/?category=stock&utm_source=toutiao&widen=1&max_behot_time=0&max_behot_time_tmp=0&tadrequire=true&as=A1C51CD5E0C5598&cp=5C50D50599C8BE1&_signature=4tjOJQAAvpNI946lUObjM-LYzj"

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3610.2 Safari/537.36",
    "Connection": "close"
}

response = requests.get(url=url,headers=headers)
response.encoding = "utf-8"
page_text = json.loads(response.text)  # 获取页面内容
# print(page_text)

data = page_text['data']  # 获取data
# print(data)
news_dict = {}  # 存放每条新闻信息的字典
news_list = []  # 存放所有新闻信息的列表
for news in data:
    news_dict['描述'] = news['abstract']
    news_dict['标题'] = news['title']
    news_dict['来源'] = news['source']
    news_dict['关键字'] = news['label']
    news_list.append(news_dict)
    news_dict={}

print(news_list)