#!/usr/bin/evn python
# -*- coding: utf-8 -*-
import os
import time
import requests
from docx import Document
from docx.shared import Inches
class MyObject(object):
def __init__(self):
self.doc = Document()
def get_url(self, id):
response = requests.get('http://***/img/pict-%d.png' % id)
pic_dic = "%s.jpg" % str(id)
with open(pic_dic, "wb")as f:
f.write(response.content)
self.doc.add_picture(pic_dic, width=Inches(6)) # 添加图, 设置宽度
os.remove(pic_dic)
def main(self):
for id in range(1, 42):
self.get_url(id)
self.doc.save('XXX.docx')
if __name__ == '__main__':
t0 = time.time()
mo = MyObject()
mo.main()
print("耗时:", time.time() - t0)
不知道如何直接保存爬取的图片到docx,只能先保存图片,在保存到docx,再删除图片。
doc.add_picture(pic_dic)
安装: pip install python-docx