如果您觉得有帮助,麻烦点赞鼓励谢谢
- 这里保存为Excel表格,用到了openpyxl库。首先建立一个工作对象,然后再操作写入
- 这里还用到了正则匹配,我们首先是把网页爬下来看一下结构,然后根据需要,找正则表达式
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/58.0.3029.110 Safari/537.36 SE 2.X MetaSr 1.0"}
res = requests.get(url, headers=headers)
return res
def find_data(res):
data = []
soup = bs4.BeautifulSoup(res.text,"html.parser")
content = soup.find(id="Cnt-Main-Article-QQ")
target = content.find_all("p",style="TEXT-INDENT: 2em")
target = iter(target)#把target变为迭代器,下面才能用next
for each in target:
if each.text.isnumeric():
data.append([
re.search(r'\[(.+)\]',next(target).text).group(1),
re.search(r'\d.*',next(target).text).group(),
re.search(r'\d.*',next(target).text).group(),
re.search(r'\d.*',next(target).text).group()])
return data
def to_excel(data):
wb = openpyxl.Workbook()
#让openpxyl 自动识别保存的是文本格式还是数值格式
wb.guess_types = True
# 获取工作表
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("2017中国主要城市房价工资比排行榜.xlsx")
def main():
url = "http://news.house.qq.com/a/20170702/003985.htm"
res = open_url(url)
data = find_data(res)
to_excel(data)
# with open("houseprice.txt","w",encoding="utf-8") as file:
# file.write(res.text)
if __name__ == '__main__':
main()```