自用：python爬虫——百度图片

最新推荐文章于 2024-07-07 09:46:06 发布

麻辣鸡儿

最新推荐文章于 2024-07-07 09:46:06 发布

阅读量1k

点赞数 2

本文链接：https://blog.csdn.net/u011628171/article/details/79004548

版权

#coding: utf-8
import os
import re
import time
import urllib.request

def getHtml(url):
    print(url)
    page=urllib.request.urlopen(url)
    html=page.read()
    return html

def getImg(html):
    reg=r'"objURL":"(.*?)"'   #正则
    # 括号表示分组，将括号的内容捕获到分组当中
    #  这个括号也就可以匹配网页中图片的url了
    imgre=re.compile(reg)
    html = html.decode('utf-8')
    imglist=re.findall(imgre,html)
    l=len(imglist)
    return imglist

def downLoad(urls,path):
    index = (page - 1) * 30 + 1
    for url in urls:
        time.sleep(1)
        try:
            res = urllib.request(url)
            if str(res.status_code)[0] != "200":
                continue
        except Exception as e:
            print(e)

        filename = os.path.join(path, str(index) + ".jpg")
        try:
            urllib.request.urlretrieve(url, filename)  # 直接将远程数据下载到本地。
            index += 1
        except Exception as e:
            print(e)
            continue

def url(page):
    html =getHtml("https://image.baidu.com/search/index?tn=baiduimage&ie=utf-8&word=%E8%AF%81%E4%BB%B6%E7%85%A7&rn=30&pn="+str((page-1)*30))
    return html

Savepath="G:/IMG"

page = 0;
while 1 :
    page = page+1
    downLoad(getImg(url(page)),Savepath)
    time.sleep(1)