Python 爬取百度图片

百度图片抓包数据:

参数详情:

数据解析:

from urllib import request, parsefrom http import cookiejarimport reimport 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()    passa=0while 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)    passprint("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.