[原创]python爬虫之BeautifulSoup,爬取网页上所有图片标题并存储到本地文件

from bs4 import BeautifulSoup
import requests
import re
import os
r = requests.get("https://re.jd.com/search?keyword=%E6%B0%B4%E6%9E%9C%20%E7%BD%91&keywordid=44195495794&re_dcp=202m0QjIIg==&traffic_source=1004&test=1&enc=utf8&cu=true&utm_source=baidu-search&utm_medium=cpc&utm_campaign=t_262767352_baidusearch&utm_term=44195495794_0_32d58cbc7f0f40e08d64a09fbc8c95c4")
result = r.content
# print(result)
soup = BeautifulSoup(result,"html.parser")
# print(soup.script.text)
souptext = soup.find(type='text/javascript').text
# print(souptext)

pattern3 =re.compile(r'\"ad_title_text\":\"(.*?\"),\"image_url\":\"(.*?\.(jpg|png))\"')
patternresult3 = pattern3.findall(souptext)
print(patternresult3)

j = 0
for i in patternresult3:
    j = j+1
    title = i[0].replace(' ','').replace('\"','1').replace('/','1')
    with open(os.getcwd()+'\\jpg\\'+title+str(j)+"."+i[2],"wb") as f: #在执行代码前,需要先创建一个jpg的目录,os.getcwd()用来获取当前目录
        f.write(requests.get("https://img1.360buyimg.com/n6/"+i[1]).content)

运行结果如下:

 

转载于:https://www.cnblogs.com/lelexiong/p/10869451.html