python爬取百度图片

介绍

　　学了python两天左右弄懂了这个爬虫，然后呢我也是小白，
发这个贴子主要是记录学习心得（大佬回避 ）

先写一个简单示例
如下：

import request#引入库

url 'http://baidu.com'  #设置爬取网页
res = requests.get(url)#get请求
print(res.text)#打印输出
json取值
re正则表达式替换内容
open保存

模块安装方法

下面为爬取百度图片代码

ps：需要再D盘新建image文件夹
否则会报错
如下：

代码

import re
# 正则表达式
import requests
# import datetime
import os

name = input('请输入图片昵称')

headers = {
    'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 13_2_3 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.0.3 Mobile/15E148 Safari/604.1 Edg/109.0.0.0',
    'Cookie': 'BIDUPSID=6946D6FF83F5BB7F59A255D96C8655A1; PSTM=1673689509; BAIDUID=6946D6FF83F5BB7FFE94DCA671784D4E:FG=1; BDUSS=FBvUThma1JEQ0s5Y2lITGlPUTlBVDd3SDdFMU00dXdwNWE0d35CbWtSek9OZ1JrSUFBQUFBJCQAAAAAAAAAAAEAAABFzoozY2hlbm51b2tlamkAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAM6p3GPOqdxjT; BDUSS_BFESS=FBvUThma1JEQ0s5Y2lITGlPUTlBVDd3SDdFMU00dXdwNWE0d35CbWtSek9OZ1JrSUFBQUFBJCQAAAAAAAAAAAEAAABFzoozY2hlbm51b2tlamkAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAM6p3GPOqdxjT; BDSFRCVID=I1kOJeC6275VcNojIB9aui_0SmkdVk7TH6_nezkj1ADf7HHyXk7WEG0PBM8g0KubRyJSogKKLmOTHpCF_2uxOjjg8UtVJeC6EG0Ptf8g0f5; H_BDCLCKID_SF=JnPeVItatIK3qnO4DITS2tI0-eT22jPjWec9aJ5nJDobVDJRQJj8-T50Qho0Qb5My6rbhxjvQpP-_nrv5b3kBP5XLxLO2ncMBIOmKl0MLpoYbb0xynoYbUPq2MnMBMnramOnaPJn3fAKftnOM46JehL3346-35543bRTLnLy5KJtMDFRDTLMejOXjHR22Pc22-oKWnTXbRu_Hn7zeUuaMU4pbt-qJj-tQD7wWbcY0DTHfJT3DhbVMP0ZMNJnBT5daDTEBbFh0lbtMpnS2q7Ojp-kQN3T3fuO5bRiLRo4Mlc6Dn3oyUvVXp0nK-bly5jtMgOBBJ0yQ4b4OR5JjxonDh83bG7MJPKtfD7H3KChtCt5hU5; H_PS_PSSID=36559_37551_37518_38091_38124_37910_37990_37795_36803_37933_38086_38041_26350_37957_38100_38008_37881; BAIDUID_BFESS=6946D6FF83F5BB7FFE94DCA671784D4E:FG=1; BDSFRCVID_BFESS=I1kOJeC6275VcNojIB9aui_0SmkdVk7TH6_nezkj1ADf7HHyXk7WEG0PBM8g0KubRyJSogKKLmOTHpCF_2uxOjjg8UtVJeC6EG0Ptf8g0f5; H_BDCLCKID_SF_BFESS=JnPeVItatIK3qnO4DITS2tI0-eT22jPjWec9aJ5nJDobVDJRQJj8-T50Qho0Qb5My6rbhxjvQpP-_nrv5b3kBP5XLxLO2ncMBIOmKl0MLpoYbb0xynoYbUPq2MnMBMnramOnaPJn3fAKftnOM46JehL3346-35543bRTLnLy5KJtMDFRDTLMejOXjHR22Pc22-oKWnTXbRu_Hn7zeUuaMU4pbt-qJj-tQD7wWbcY0DTHfJT3DhbVMP0ZMNJnBT5daDTEBbFh0lbtMpnS2q7Ojp-kQN3T3fuO5bRiLRo4Mlc6Dn3oyUvVXp0nK-bly5jtMgOBBJ0yQ4b4OR5JjxonDh83bG7MJPKtfD7H3KChtCt5hU5; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; BDRCVFR[dG2JNJb_ajR]=mk3SLVN4HKm; BDRCVFR[-pGxjrCMryR]=mk3SLVN4HKm; delPer=0; IMG_BR_CLK=YES; POLYFILL=0; BDRCVFR[5GQZCjFg8mf]=mk3SLVN4HKm; ab_sr=1.0.1_Y2UwMDJiOTgzODExZGRmNWNiZDZhZmFmYTNlNzNmMzE2NDM0ZTI4MjRhMGNlMzZkZWI3MTA3MzdmMDZjYzZiNDhkNTQyYTQzYjBiNzI4YWE4MDRhOTY3Zjk5OTlkOGU5ZGNhODYwODFiMjQwMzdkYzdmNTc0YjVjNDBkZjlmM2ZmYTg2NjJjYTUwNDg4ZWUyZjUwNmU2ZTJhZDQxZWUzNjFmODdiYjVjZGFhYzk3MjNkMWMyMzczN2JmMmY4OTgz; rsv_i=1e31gfvK1rhsKKtKfksQcSANe+lsro6kfEPZTgy+Ci5xZ0uX9nqXd72/2fslVEVzRdCcOf7F61kR6E2c458F4oldTFgZv4I; BDSVRTM=316; IMG_WH=966_1196; BDSVRBFE=Go; H_WISE_SIDS=219946_232280_231979_234925_219623_237837_232777_232055_236810_234020_232247_238890_238413_240447_240465_240790_239491_216844_213345_229967_214798_235965_219943_213042_204909_241245_238073_230288_240965_242157_242311_241698_242546_242489_242753_242757_242545_242900_242336_239308_110085_240597_227869_242188_234208_243510_236308_243594_242517_243642_243842_243706_242128_243874_241737_244320_244311_244007_244398_244032_244641_232628_244725_243425_244769_244830_240595_244957_245003_242380_242374_235442_239851_243208_245083_245271_197096_244446_245412_242682_245234_244984_245472_245519_245501_245511_245509_245563_245653_224436_245763_245771_8000059_8000108_8000113_8000133_8000136_8000149_8000155_8000162_8000165_8000172_8000177_8000183_8000185_8000190; H_WISE_SIDS_BFESS=219946_232280_231979_234925_219623_237837_232777_232055_236810_234020_232247_238890_238413_240447_240465_240790_239491_216844_213345_229967_214798_235965_219943_213042_204909_241245_238073_230288_240965_242157_242311_241698_242546_242489_242753_242757_242545_242900_242336_239308_110085_240597_227869_242188_234208_243510_236308_243594_242517_243642_243842_243706_242128_243874_241737_244320_244311_244007_244398_244032_244641_232628_244725_243425_244769_244830_240595_244957_245003_242380_242374_235442_239851_243208_245083_245271_197096_244446_245412_242682_245234_244984_245472_245519_245501_245511_245509_245563_245653_224436_245763_245771_8000059_8000108_8000113_8000133_8000136_8000149_8000155_8000162_8000165_8000172_8000177_8000183_8000185_8000190; __bsi=11641568841083099398_00_28_R_R_17_0303_c02f_Y',
    'Referer': 'https://m.baidu.com/sf/vsearch?pd=image_content&word=jk&tn=vsearch&atn=page'
    # 模拟请求头
}
if not os.path.exists('D:/image/'):
    os.mkdir(('D:/image/'))
for page in range(1,10):
    url = f"https://image.baidu.com/search/acjson?tn=resultjson_com&logid=12112874779582819460&ipn=rj&ct=201326592&is=&fp=result&fr=&word={name}&queryWord={name}&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=&z=&ic=&hd=&latest=&copyright=&s=&se=&tab=&width=&height=&face=&istype=&qc=&nc=1&expermode=&nojc=&isAsync=&pn={page * 30}&rn=30&gsm=1e&1677171694590="
    # 请求链接

    response = requests.get(url=url, headers=headers)
    # requests.get获取数据
    p_url = response.json()['data']
    # json取值
    
    for i in range(29):
        img_url = p_url[i]['hoverURL']
        # 取图片链接
        img_title = p_url[i]['fromPageTitle']
        title = re.sub('[\\/:*?<>✘|\\n#@)\》》】【—_\-# - \."\《(\r]', ' ', img_title)
        # 取图片标题
        print(title, img_url, '√')

        # 正则表达式替换特殊符号

        res = requests.get(url=img_url, headers=headers)
        # get请求数据

        with open(f'D:/image/{title}''.jpg', mode='wb') as f:
            # 设置保存路径，写入格式
            f.write(res.content)
        # 保存