from bs4 import BeautifulSoup
import requests
from fake_useragent import UserAgent
import csv

# 預(yù)加載寫入的文件
f = open('價(jià)格表.csv', mode='w', newline='')
csvwirter = csv.writer(f)

# 偽裝UA
ua = UserAgent()
heard = {
    "User-Agent": ua.firefox
}

# 初始化URL.get方法請(qǐng)求
url = 'https://www.lvguo.net/baojia'
resp = requests.get(url, headers=heard, )

# 實(shí)例化bs4對(duì)象
page = BeautifulSoup(resp.text, features="html.parser")  # features="html.parser" 標(biāo)記傳入的數(shù)據(jù)為html數(shù)據(jù) 

# 查找標(biāo)記為table class=bjtbl的數(shù)據(jù)
table = page.find('table', attrs={"class": "bjtbl"})

# 找到所有包含 tr 的數(shù)據(jù),返回值為list  tr[1:] 切除數(shù)據(jù)注釋行
tr = table.find_all('tr')
trs = tr[1:]

# 遍歷每行的數(shù)據(jù)
for i in trs:
    # 查找標(biāo)記為td的數(shù)據(jù)
    td = i.find_all('td')
    time = td[0].text
    adress = td[1].text
    name = td[2].text
    # 數(shù)據(jù)拆分
    type = td[3].text.split("\n")[0].split('：')[0]
    price = td[3].text.split("\n")[0].split('：')[1] + td[3].text.split("\n")[1]
    # 數(shù)據(jù)寫入
    csvwirter.writerow([time, adress, name, type, price])

f.close()