1 # coding: utf-8
 2 import urllib   #用urllib库进行页面爬取
 3 from urllib.request import urlopen,Request      #用request进行页面有关的操作
 4 from bs4 import BeautifulSoup as bs
 5 import chardet  #查看页面的编码类型
 6 from openpyxl import workbook  # 写入Excel表所用
 7 from openpyxl import load_workbook  # 读取Excel表所用
 8 import os
 9 os.chdir(‘C:\Users\Admin\Desktop‘)  # 更改工作目录为桌面
10 
11 # 爬取网页
12 def getHtml(address, headers)
13     url = Request(url=address, headers=headers)
14     html = urlopen(url).read()
15     #charset = chardet.detect(html)    #查看编码类型
16     #print(charset)    #打印编码类型
17     html = html.decode(‘utf-8‘)
18     return html
19 
20 def getTable(html)
21     soup = bs(html, ‘html.parser‘)  # 将读取到的网页代码用指定解析器html.parser进行解析
22     tables = soup.find_all(‘div‘)
23 
24 if __name__ == ‘__main__‘:
25     #   读取存在的Excel表测试
26     #     wb = load_workbook(‘test.xlsx‘) #加载存在的Excel表
27     #     a_sheet = wb.get_sheet_by_name(‘Sheet1‘) #根据表名获取表对象
28     #     for row in a_sheet.rows: #遍历输出行数据
29     #         for cell in row: #每行的每一个单元格
30     #             print cell.value,
31 
32     #  创建Excel表并写入数据
33     wb = workbook.Workbook()    # 创建Excel对象
34     ws = wb.active               # 获取当前正在操作的表对象
35     # 往表中写入标题行,以列表形式写入！
36     ws.append([‘信息页‘, ‘公司名称‘, ‘主营产品‘, ‘联系人‘, ‘电话‘])
37     headers = {‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/79.0.3945.88 Safari/537.36‘}
38     address = ‘http://b2b.huangye88.com/wuxi/zhuangxiuzhuangshi9586/pn2/‘
39     html = getHtml(address, headers)
40     getTable(html)