Python 爬虫BeautifulSoup（bs4）基本使用

# 1 拿到页面源代码
# 2 使用bs4进行解析，拿到数据
import requests
from bs4 import BeautifulSoup
import csv

url = "http://www.xinfadi.com.cn/priceDetail.html"
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 Safari/537.36 SLBrowser/7.0.0.12151 SLBChan/30"

}
resp = requests.get(url, headers=headers).content

f = open("菜价.csv", mode="w")
csvwriter = csv.writer(f)

# 解析数据
# 1. 把页面源代码交给BeautifulSoup进行处理，生成bs对象
page = BeautifulSoup(resp.text, "html.parser")  # 指定html解析器
# 2 从bs对象中查找数据
# find（标签，属性=值）
# find_all(标签，属性=值)
table = page.find("thead")  # class是python的关键字
print(table)
# 拿到所有数据行
csvwriter.writerow([table])
trs = table.find_all("tr")[1:]
for tr in trs:  # 每一行
    ths = tr.find_all("th")  # 拿到每行中的所有td
    name = ths[0].text  # .text 表示拿到被标签标记的内容
    low = ths[1].text
    avg = ths[2].text
    high = ths[3].text
    gui = ths[4].text
    kind = ths[5].text
    date = ths[6].text
    csvwriter.writerow([name, low, high, gui, kind, date])

f.close()
resp.close()
print("over!!!!")