记一次对选美网站的爬取

#-*- coding:utf-8 -*-
__author__ = "MuT6 Sch01aR"

import requests
from bs4 import BeautifulSoup
import sys
import io
  
sys.stdout = io.TextIOWrapper(sys.stdout.buffer,encoding='gb18030')

respons = requests.get(
    url = "http://www.baidu.com"
)

respons.encoding = respons.apparent_encoding

soup = BeautifulSoup(respons.text,features="html.parser")

target = soup.find('table',attrs={'class':'ListProduct'})

tr_list = target.find_all("tr")

for i in tr_list[1:200]:
    td_list = i.find_all("td")
    img_url = i.find_all('img')
    #txt = "姓名："+td_list[0].text,"照片："+"http://www.baidu.com/"+td_list[1].find('img').attrs.get("src"),"http://www.baidu.com/"+td_list[2].find('img').attrs.get("src"),"http://www.baidu.com/"+td_list[3].find('img').attrs.get("src"),"http://www.baidu.com/"+td_list[4].find('img').attrs.get("src"),"http://www.baidu.com/"+td_list[5].find('img').attrs.get("src"),"电话："+td_list[6].text,"信息："+td_list[7].text,"报名日期："+td_list[8].text,"微信号："+td_list[9].text
    #img_urls = "http://www.baidu.com/"+td_list[1].find('img').attrs.get("src"),"http://www.baidu.com/"+td_list[2].find('img').attrs.get("src"),"http://www.baidu.com/"+td_list[3].find('img').attrs.get("src"),"http://www.baidu.com/"+td_list[4].find('img').attrs.get("src"),"http://www.baidu.com/"+td_list[5].find('img').attrs.get("src")
    txt = "姓名："+td_list[0].text,"电话："+td_list[6].text,"信息："+td_list[7].text,"报名日期："+td_list[8].text,"微信号："+td_list[9].text
    file_name = td_list[0].text + ".txt"
    with open(file_name,"wb") as s:
        s.write(bytes(str(txt).encode("utf-8")))
    for a in range(1,6):
        if td_list[a].find('img').attrs.get("src") != "":
            img_urls = "http://www.baidu.com/" + td_list[a].find('img').attrs.get("src")
            img_response = requests.get(url=img_urls)
            file_name1 = td_list[0].text+str(a)+ ".jpg"
            with open(file_name1,"wb") as f:
                f.write(img_response.content)
print("++++++++++++++++爬行结束+++++++++++++++")