爬蟲之汽車之家（request）

#!/usr/bin/env python
#-*- coding:utf-8 -*-
# requests:用來下載網頁源代碼的,等同urlopen()
#Beautiful Soup，解析html,替代正則部分re
#Html
#BeautifulSoup().find("a")
import requests
import bs4
from bs4 import BeautifulSoup

#拿到汽車之家的首頁源代碼
#urlopen(url).read.decode
main_page_content=requests.get("https://www.autohome.com.cn/weifang/").text
#把頁面源代碼交給bs4解析
main_page=BeautifulSoup(main_page_content,"html.parser")
#可以進行標簽的定位
main_div=main_page.find(name="div",attrs={"class":"people-content"})
main_ul=main_div.find(name="ul",attrs={"class":"list-text"})
main_a_lst=main_ul.find_all("a")#這是一個列表，a標簽列表
n=1
for a in main_a_lst:
    #從標簽中獲取一個屬性
    one_page_url="https:"+a.get("href")
    print("====>",one_page_url)
    one_page_content=requests.get(one_page_url).text
    one_page_content=one_page_content.replace("</br>","")#替換掉所有的</br>
    one_page=BeautifulSoup(one_page_content,"html.parser")
    img_lst=one_page.find("div",attrs={"class":"journey-item-list"}).find_all("img")
    for img in img_lst:
        #拿到圖片的的src
        download_url=img.get("data-original")
        if not download_url:
            download_url = img.get("src")
        print(download_url)
        #下載圖片
        f = open("img/汽車之家圖片%s.jpg"% n,mode="wb")
        f.write( requests.get(download_url).content)
        f.close()
        n=n+1
        print("你成功的從汽車之家偷走了一張圖片")