Discuss / Python / 用了bs4完成了
Back

用了bs4完成了

Topic source

水滴竹沙

#1 Created at ... [Delete] [Delete and Lock User] 
from urllib import request
from bs4 import BeautifulSoup

def fetch_xml(url):
    req=request.Request(url)
    page=request.urlopen(req)
    f=page.read()
    soup=BeautifulSoup(f,'html.parser')
    count=0   
    for i in soup.select('div[class="D(ib) Va(m) W(1/4)"]'):
        count=count+1

    for j in range(count):
        print('星期:',soup.select('div[class="D(ib) Va(m) W(1/4)"]')[j].get_text())
        print('天气:',soup.select('span[class="D(ib) Va(m) W(1/4) Ta(c)"] > img')[j]['title'])
        a=soup.select('span[class="D(ib) Va(m) W(1/4) Ta(end)"]')[j].get_text()
        print('温度:','high:%sF, low:%sF'%(a[0:3],a[3:6]))
        print('-'*30)



fetch_xml('https://www.yahoo.com/news/weather/china/beijing/beijing-2151330')

西湖水中沙

#2 Created at ... [Delete] [Delete and Lock User]

Beautiful soup 很强大 我copy了你的代码

import os
from urllib import request
from bs4 import BeautifulSoup

'html_code.txt contains the source code of url'

def fetch_xml(url):
    # req = request.Request(url)
    # page = request.urlopen(req)
    # f = page.read()
    file_path = os.path.join(os.path.dirname(__file__), 'html_code.txt')
    f = open(file_path, 'r').read()
    soup = BeautifulSoup(f, 'html.parser')

    for j in soup.findAll('div', {'class': 'BdB Bds(d) Bdbc(#fff.12) Fz(1.2em) Py(2px) O(0) Pos(r) forecast-item'}):
        print('星期:', j.find('div', class_="D(ib) Va(m) W(1/4)").text)
        print('天气:', j.select('span[class="D(ib) Va(m) W(1/4) Ta(c)"] > img')[0]['title'].strip())
        a = j.select('span[class="D(ib) Va(m) W(1/4) Ta(end)"]')[0].get_text()
        print('温度:', 'high:%sF, low:%sF' % (a[0:3], a[3:6]))
        print('-' * 30)

if __name__ == "__main__":
    fetch_xml()

Thanks

  • 1

Reply