Python 爬取百度图片

不念不忘少年蓝@ 2022-06-05 09:25 311阅读 0赞

百度图片抓包数据:  
![SouthEast][]  
参数详情:  
![SouthEast 1][]  
数据解析:  
![SouthEast 2][] ![SouthEast 3][]

from urllib import request, parse
    from http import cookiejar
    import re
    import time
    
    
    # 1.提取数据
    def main(text,start,length):
        hx = hex(start)
        s = str(hx)[2:len(hx)]
        reqMessage = {
            "tn": "resultjson_com",
            "ipn": "rj",
            "ct": "201326592",
            "is": "",
            "fp": "result",
            "queryWord": text,
            "cl": "2",
            "lm": "-1",
            "ie": "utf-8",
            "oe": "utf-8",
            "adpicid": "",
            "st": "",
            "z": "",
            "ic": "",
            "word": text,
            "s": "",
            "se": "",
            "tab": "",
            "width": "",
            "height": "",
            "face": "",
            "istype": "",
            "qc": "",
            "nc": "",
            "fr": "",
            "cg": "head",
            "pn": str(start),
            "rn": str(length),
            "gsm": s,
            "1511330964840": ""
        };
        cookie=cookiejar.CookieJar()
        cookie_support = request.HTTPCookieProcessor(cookie)
        opener = request.build_opener(cookie_support, request.HTTPHandler)
        request.install_opener(opener)
    
        reqData = parse.urlencode(reqMessage)
        req = request.Request("http://image.baidu.com/search/acjson?" + reqData, headers={
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36"})
        data = request.urlopen(req).read();
    
        rm = re.compile(r'"thumbURL":"[\w/\\:.,;=&]*"')
        list = re.findall(rm, data.decode())
    
        index = start+1
        result=False
        for thumbURL in list:
            url = thumbURL[12:len(thumbURL) - 1]
            downImg(url, "F:/file/baidu/" + str(index) + ".jpg")
            index += 1
            result=True
    
        return result
    
    # 下载图片
    def downImg(url, path):
        print(url)
    
        req=request.Request(url,headers={
       "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36",
                                         "Referer":"http://image.baidu.com/search/acjson"})
        data= request.urlopen(req).read()
    
        file=open(path,"wb")
        file.write(data)
        file.close()
        pass
    
    a=0
    while a!=-1:
        result= main("美女图片", a*30, 30)
        print("暂停中...")
        a += 1
        if result==False :
            a=-1
        time.sleep(10)
        pass
    
    print("执行完成")

信息不多没有什么太多的事情,需要注意的就是下载图片时请求头需要添加User-Agent以及Referer,否则百度会拒绝访问,另外百度的图片只能访问一次,访问一次过后图片链接立即失效.还有抓取的数据以及时间限制,一次性爬取的数量有限.

[SouthEast]: /images/20220605/9a5c7ab1ce2f46188796d6ad0ef68873.png
[SouthEast 1]: /images/20220605/cc18db24019c4ba7a16db3a4360ade0b.png
[SouthEast 2]: https://img-blog.csdn.net/20171123160117781?watermark/2/text/aHR0cDovL2Jsb2cuY3Nkbi5uZXQvdzE4NzU2OTAxNTc1/font/5a6L5L2T/fontsize/400/fill/I0JBQkFCMA==/dissolve/70/gravity/SouthEast
[SouthEast 3]: /images/20220605/5bd5e8029c2d4cd2b4cd2ce18167a880.png