bs4练手-gp网

import requests  # 爬虫 爬数据
from urllib import request  # 下载图片
from bs4 import BeautifulSoup

headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36 Edg/125.0.0.0'
}

# 1.数据要么在网页源码 html
# 2. 数据要么在接口里面(检查=>网络=>找接口url)
url = "https://quote.stockstar.com/stock/stock_index.htm"

# 开始爬虫

res = requests.get(url, headers=headers)
# result = res.text   # 如果是utf-8可以直接解析
# result = res.content.decode()   # 解析出现中文乱码  可以用这个  字节类型 => 字符串
result = res.content.decode('GBK')
# print(result)  # <class 'str'>

# 2.解析html源码
soup = BeautifulSoup(result,"lxml")
li_list = soup.select('#index_data_0 li')

# 遍历每一个li(每一个企业)
for li in li_list:
    # 股票代码
    code = li.select('a')[0].text
    # 企业名称
    name = li.select('a')[1].text
    print(code, name)