精易论坛

标题: 爬取百度图片 [打印本页]

作者: ideologism 时间: 2019-1-5 15:12
标题: 爬取百度图片
import re
import requests
from requests.exceptions import RequestException
from multiprocessing import Pool

word = '油菜'
def dowmloadPic(i):

url = 'http://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word=' + word + '&ct=201326592&v=flip'
result = requests.get(url)
html = result.text
pic_url = re.findall('"objURL":"(.*?)",', html, re.S)

print('找到关键词:' + word + '的图片，现在开始下载图片...')
for each in pic_url:
      print('正在下载第' + str(i) + '张图片，图片地址:' + str(each))
      try:
         pic = requests.get(each, timeout=10)

      except RequestException:
         print('【错误】当前图片无法下载')
         continue

      dir = 'images/' + word + '_' + str(i) + '.jpg'
      fp = open(dir, 'wb')
      fp.write(pic.content)
      fp.close()
      i += 1

if __name__ == '__main__':

pool = Pool()
pool.map(dowmloadPic,[i for i in range(600)])

作者: 等闲之辈 时间: 2023-11-27 13:47
感谢分享~

欢迎光临精易论坛 (https://125.confly.eu.org/)