爬房价表，正则表达式group函数报错

xiaoyuu

import requests
import bs4
import re
import openpyxl
def open_url(url):
    headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'}

    res = requests.get(url,headers=headers)
    return res
def find_word(res):
    soup = bs4.BeautifulSoup(res.text,'lxml')
    content = soup.find("article",id="mp-editor")
    targets = content.find_all("td")
    targets = iter(targets)

    data = []
    for each in targets:
        if each.text.isnumeric():
            data.append([
                re.search(r'<td>(\d.*)</td>',next(targets).text).group(1),
                re.search(r'<td>(\w.*)</td>',next(targets).text).group(),
                re.search(r'<td>(\d.*)</td>',next(targets).text).group(),
                re.search(r'<td>(\w.*)</td>',next(targets).text).group(),
                re.search(r'<td>(\w.*)</td>',next(targets).text).group(),
                re.search(r'<td>(\w.*)</td>',next(targets).text).group(),
                re.search(r'<td>(\w.*)</td>',next(targets).text).group()
            ])
    return data

def save_exal(data):
    wb = openpyxl.Workbook()
    wb.guess_types = True
    ws = wb.active
    ws.append("排名","城市","中位房价","级别","省份","市场等级","区域")
    for each in data:
        ws.append(each)
    wb.save("2018房价工资比.xlsx")

def main():
    host = 'https://www.sohu.com/a/230135374_119746'
    res = open_url(host)
    data = find_word(res)


    save_exal(data)

if __name__ =="__main__":
    main()

报错信息如下：
Traceback (most recent call last):
  File "E:/untitled/2018房价工资比.py", line 62, in <module>
    main()
  File "E:/untitled/2018房价工资比.py", line 55, in main
    data = find_word(res)
  File "E:/untitled/2018房价工资比.py", line 23, in find_word
    re.search(r'<td>(\d.*)</td>',next(targets).text).group(1),
AttributeError: 'NoneType' object has no attribute 'group'


哪位大佬可以帮看一下？？

塔利班

正则不对，没捕获到

塔利班

重点不是正则，是你用了迭代器，
for each in targets:
        if each.text.isnumeric():
            data.append([
                re.search(r'<td>(\d.*)</td>',next(targets).text).group(1),
each.text是1时。next（targets）.text就是北京，北京肯定不是数字
targets本身被迭代的时候你又用了迭代方法

塔利班

1. def find_word(res):
   
2.     soup = bs4.BeautifulSoup(res.text,'lxml')
   
3.     content = soup.find("article",id="mp-editor")
   
4.     targets = content.find_all("tr")
   
5.     data=[e.text.split('\n')[1:-1] for e in targets[1:]]
   
6.     #print(data)
   
7.     return data

复制代码

这么改下

xiaoyuu

塔利班 发表于 2018-9-25 19:17
这么改下

哈哈，谢谢，已经解决了