【Python】网络爬虫获取图片

代码1：

import os
import time
import requests
import re
def imgdata_set(save_path,word,epoch):
    q=0     #停止爬取图片条件
    a=0     #图片名称
    while(True):
        time.sleep(1)
        url="https://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word={}&pn={}&ct=&ic=0&lm=-1&width=0&height=0".format(word,q)
        #word=需要搜索的名字
        headers={
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.96 Safari/537.36 Edg/88.0.705.56'
        }
        response=requests.get(url,headers=headers)
        # print(response.request.headers)
        html=response.text
        # print(html)
        urls=re.findall('"objURL":"(.*?)"',html)
        # print(urls)
        for url in urls:
            print(a)    #图片的名字
            response = requests.get(url, headers=headers)
            image=response.content
            with open(os.path.join(save_path,"{}.jpg".format(a)),'wb') as f:
                f.write(image)
            a=a+1
        q=q+20
        if (q/20)>=int(epoch):
            break
if __name__=="__main__":
    save_path = input('你想保存的路径：')
    word = input('你想要下载什么图片？请输入:')
    epoch = input('你想要下载几轮图片？请输入(一轮为60张左右图片):')  # 需要迭代几次图片
    imgdata_set(save_path, word, epoch)

代码2： 

import requests
import re
import os
import time
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.125 Safari/537.36'}
name = input('您要爬取什么图片')
num = 0
num_1 = 0
num_2 = 0
x = input('您要爬取几张呢?，输入1等于60张图片。')
list_1 = []
for i in range(int(x)):
    name_1 = os.getcwd()
    name_2 = os.path.join(name_1,'图片')
    url = 'https://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word='+name+'&pn='+str(i*30)
    #https://image.baidu.com/search/index?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&sf=1&fmq=&pv=&ic=0&nc=1&z=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&ie=utf-8&fm=index&pos=history&word=
    res = requests.get(url,headers=headers)
    htlm_1 = res.content.decode()
    a = re.findall('"objURL":"(.*?)",',htlm_1)
    if not os.path.exists(name_2):
        os.makedirs(name_2)
    for b in a:
        try:
            b_1 = re.findall('https:(.*?)&',b)
            b_2 = ''.join(b_1)
            if b_2 not in list_1:
                num = num +1
                img = requests.get(b)
                f = open(os.path.join(name_1,'图片',name+str(num)+'.jpg'),'ab')
                print('---------正在下载第'+str(num)+'张图片----------')
                f.write(img.content)
                f.close()
                list_1.append(b_2)
            elif b_2 in list_1:
                num_1 = num_1 + 1
                continue
        except Exception as e:
            print('---------第'+str(num)+'张图片无法下载----------')
            num_2 = num_2 +1
            continue
print('下载完成,总共下载{}张,成功下载:{}张,重复下载:{}张,下载失败:{}张'.format(num+num_1+num_2,num,num_1,num_2))