python3制作下载器_基于python3 的百度图片下载器的实现代码

import re

import os

import requests

import hashlib

def dowmloadPic(html, keyword):

pic_url = re.findall('"objURL":"(.*?)",', html, re.S)

if len(pic_url) < 1:

return 1

i = 0

for each in pic_url:

print(i + 1, end=',')

md5Str = hashlib.md5(each.encode("utf-8")).hexdigest()

# 抓去链接

oneStr = md5Str + ' ' + keyword + ' ' + each + '\n'

with open('downText.txt', 'a+') as f:

f.write(oneStr)

# 下载图片

# try:

# pic = requests.get(each, timeout=10)

# except requests.exceptions.ConnectionError:

# print('链接超时,跳过此操作')

# continue

#

# kz = os.path.splitext(each)[-1]

# photo = + keyword + '_' + str(i) + kz

#

# with open(photo, 'wb') as f:

# f.write(pic.content)

i += 1

print('\n')

return 0

if __name__ == '__main__':

word = input('enter a key word:')

page = input('enter the page:')

page = int(page)

page = 1 if page < 1 else page

url = 'http://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word=' + word + '&ct=201965323&v=flip'

p = 1

while (p <= page):

print(word + ',第[' + str(p) + ']页：')

pn = (p - 1) * 20

url = url + '&pn=' + str(pn)

result = requests.get(url).content.decode('utf-8')

code = dowmloadPic(result, word)

if code:

print('无相关数据,提前退出程序')

break

p = p + 1

print('程序结束')