爬取2019主要城市房价工资比为空列表

601971945

小白一枚  照猫画虎写的代码  爬取出来是空列表  在网上没找到解决办法
求大佬帮着看一下

爬取的url:http://www.szfce.com/gn/27107.html

import requests
from bs4 import BeautifulSoup
import re
import openpyxl

def open_url(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36'
    }

    res = requests.get(url, headers = headers)
    res.encoding = 'utf-8'
    return res


def find_data(res):
    data = []
    soup = BeautifulSoup(res.text,'lxml')
    content = soup.find('article',class_="article-content")
    targets = content.find_all('p')
    targets = iter(targets)
    for each in targets:
        if each.text.isnumeric():
            data.append([
                re.search(r'\[(.+)\]',next(targets).text).group(1),
                re.search(r'\d.*',next(targets).text).group(),
                re.search(r'\d.*',next(targets).text).group(),
                re.search(r'\d.*',next(targets).text).group()
            ])
    
    return data


def to_excel(data):
    wb = openpyxl.Workbook()
    wb.guess_types = True
    ws = wb.active
    ws.append(['城市','平均房价','平均工资','房价工资比'])
    for each in data:
        ws.append(each)

    wb.save("2019全国各大主要城市房价、工资排行榜.xlsx")


def main():
    url = 'http://www.szfce.com/gn/27107.html'
    # url = 'https://news.house.qq.com/a/20170702/003985.htm'
    res = open_url(url)
    data = find_data(res)
    to_excel(data)

if __name__ == "__main__":
    main()

snaker

给你重写了一下

import requests
from bs4 import BeautifulSoup
import re
import openpyxl

def open_url(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36'
    }

    res = requests.get(url, headers = headers)
    res.encoding = 'utf-8'
    return res


def find_data(res):
    data = []
    soup = BeautifulSoup(res.text,'lxml')
    content = soup.find('article',class_="article-content")
    targets = content.find_all('p')[8:-13]
    for i in range(len(targets)//5):
        data.append([
                re.findall(r'\[(.+)\]',targets[i*5+1].text)[0],
                re.findall(r'\d.*',targets[i*5+2].text)[0],
                re.findall(r'\d.*',targets[i*5+3].text)[0],
                re.findall(r'\d.*',targets[i*5+4].text)[0]
            ])
    return data


def to_excel(data):
    wb = openpyxl.Workbook()
    wb.guess_types = True
    ws = wb.active
    ws.append(['城市','平均房价','平均工资','房价工资比'])
    for each in data:
        ws.append(each)

    wb.save("2019全国各大主要城市房价、工资排行榜.xlsx")


def main():
    url = 'http://www.szfce.com/gn/27107.html'
    # url = 'https://news.house.qq.com/a/20170702/003985.htm'
    res = open_url(url)
    data = find_data(res)
    to_excel(data)

if __name__ == "__main__":
    main()

601971945

snaker 发表于 2020-3-23 15:23
给你重写了一下

谢谢 老哥

601971945

snaker 发表于 2020-3-23 15:23
给你重写了一下

话说老哥你知道我那种写发为啥爬出来是空的么？