python 图片爬虫

1.从网站找规律

 F12-->network-->XHR,然后图片往下拉，XHR下会出现请求内容，点击进入Header找url请求规律

2.具体下载代码如下

#!/usr/bin/env Python
# coding=utf-8

import json
import itertools
import urllib
import requests
import os
import re
import sys

# 生成网址列表
def buildUrls(word):
    word = urllib.parse.quote(word)
    url = r"https://image.baidu.com/search/acjson?tn=resultjson_com&ipn=rj&ct=201326592&is=&fp=result&queryWord={word}&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=-1&z=&ic=0&word={word}&s=&se=&tab=&width=&height=&face=0&istype=2&qc=&nc=1&fr=&pn={pn}&rn=30&gsm=78&1524745446180="
    urls = (url.format(word=word, pn=x*30) for x in range(60))
    return urls
# 解析JSON获取图片URL
re_url = re.compile(r'"thumbURL":"(.*?)"')

def resolveImgUrl(html):
    imgUrls = re_url.findall(html)
    return imgUrls


def downImg(imgUrl, dirpath, imgName):
    filename = os.path.join(dirpath, imgName)
    try:
        res = requests.get(imgUrl, timeout=15)
        if str(res.status_code)[0] == "4":
            print(str(res.status_code), ":", imgUrl)
            return False
    except Exception as e:
        print(" This is Exception：", imgUrl)
        print(e)
        return False
    with open(filename, "wb") as f:
        f.write(res.content)
    return True


def mkDir(dirName):
    dirpath = os.path.join(sys.path[0], dirName)
    if not os.path.exists(dirpath):
        os.mkdir(dirpath)
    return dirpath


if __name__ == '__main__':

    word = '鸟类'

    dirpath = mkDir("D:/getdata/down/baidu/"+word)

    urls = buildUrls(word)
    index = 0
    for url in urls:
        print("requesting：", url)
        html = requests.get(url, timeout=10).content.decode('utf-8')
        imgUrls = resolveImgUrl(html)
        if len(imgUrls) == 0:  # 没有图片则结束
            break
        for url in imgUrls:
            if downImg(url, dirpath, "baidu"+str(index) + ".jpg"):
                index += 1
                print("Downloaded %s picture" % index)