爬取百度图片

import requests

import os

import zipfile

'''

爬取百度图片

'''

imgnum = 0

def get_url(starpagenum,keyword):

params={

'tn': 'resultjson_com',

'ipn': 'rj',

'ct': '201326592',

'is': '',

'fp': 'result',

'cl': '2',

'lm': '-1',

'ie': 'utf-8',

'oe': 'utf-8',

'adpicid': '',

'st': '-1',

'z': '',

'ic':' 0',

'queryWord': keyword,

'word': keyword,

's': '',

'se': '',

'tab':'',

'width': '',

'height': '',

'face': '0',

'istype':'2',

'qc': '',

'nc': '1',

'fr':'',

'pn': starpagenum+30,

'rn': '30',

}

url = 'https://image.baidu.com/search/acjson'

request = requests.get(url,params=params)

request.encoding="utf-8"

json =request.json().get('data')

for item in json:

if item == {}:

return

yield{

'url':item.get('thumbURL'),

'name':item.get('fromPageTitleEnc')[1:10]

}

def save_imgs(imgs):

filepath = r"E:\python\pythonzong\爬虫\request\imgbaidutu\\"

for item in imgs:

url = item.get('url')

name = ''.join(item.get('name').split()).replace('*','')

global imgnum

imgnum += 1

filename = filepath+str(str(imgnum)+name+".jpg")

print(filename)

request = requests.get(url)

with open(filename,'wb') as file:

file.write(request.content)

def save_zip(newpath,path):

print("开始压缩文件")

with zipfile.ZipFile(newpath,'w',zipfile.ZIP_DEFLATED) as zp:

for path, fileparename, filename in os.walk(path): #path fileparename filename 路劲，文件夹名，文件名

for name in filename:

zp.write(os.path.join(path,name)) # 把要压缩的文件写入压缩

print("压缩文件成功")

if __name__ == '__main__':

keyword = "美女"

for num in range(0,10):

save_imgs(get_url(num,keyword))

path = r"E:\python\pythonzong\爬虫\request\imgbaidutu"

zippath = "E:\\python\\pythonzong\\爬虫\\request\\"+keyword+".zip"

save_zip(zippath,path)

这里我们可以换关键字和页数都是自己换的