1. import requests
    2. import pandas as pd
    3. import numpy as np
    4. import os
    5. import random
    6. import string
    7. import csv
    9. headers = {
    10.     # 'Host': 'i.meizitu.net',
    11.     'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
    12.     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:55.0) Gecko/20100101 Firefox/55.0',
    13.     'Accept-Language': 'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3',
    14.     'Connection': 'keep-alive',
    15.     'Accept-Encoding': 'gzip, deflate',
    16.     'Upgrade-Insecure-Requests': '1',
    17.     'content-type': "application/json"
    18. }
    20. s = requests.session()  # 保留会话
    22. # 下载图片
    23. def downIMG(url, fileName):
    24.     try:
    25.         url = str(url).split("?")[0]
    26.         LAST = str(url).split(".")[-1]
    27.                 # 没有文件夹，则创建文件夹
    28.         if not os.path.exists('D:/Image/' + fileName):  
    29.             os.mkdir('D:/Image/' + fileName)
    31.         url_re = s.get(url.strip(), headers=headers)
    32.         if url_re.status_code == 200:
    33.             open("D:/Image/" + fileName + "/" + initImageName() + "." + LAST, 'wb').write(url_re.content)
    34.     except:
    35.         with open("image-run-error.csv", "a", encoding='utf-8') as  csvfile:
    36.             writer = csv.writer(csvfile)
    37.             writer.writerow(fileName, url)
    39.  # 随机生成文件名           
    40.  def initImageName():
    41.     ran_str = ''.join(random.sample(string.ascii_letters + string.digits, 8))
    42.     return ran_str
    44. if __name__ == '__main__':
    45.     images = pd.read_csv("drug-image-url.csv")
    46.     images.fillna('', inplace=True)
    47.     images = np.array(images).tolist()
    48.     for image in images:
    49.         try:
    50.             downIMG(image[2], image[0] + "," + str(image[1]).replace("*", "_"))
    51.         except:
    52.           continue