parse live.caipiao.163.com

caipiao.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import requests
from bs4 import BeautifulSoup


soup = BeautifulSoup(requests.get("http://live.caipiao.163.com/jcbf/").text)
# soup = BeautifulSoup(requests.get("http://live.caipiao.163.com/dcbf/").text)
dd = soup.find_all("dd")
final_list = []
for i in dd:
    final_list.append(
        {
            "matchid": i.get("matchid"),
            "hostid": i.get("hostid"),
            "visitid": i.get("visitid"),
            "period": i.find("span", class_="period").string,
            "events": i.find("span", class_="events").string,
            "playTime": i.find("span", class_="playTime").string,
            "round": i.find("span", class_="round").string,
            "type": i.find("span", class_="type").string,
            "host": i.find("span", class_="host").text.split()[1],
            "guest": i.find("span", class_="guest").text.split()[0],
            "half": i.find("span", class_="half").string,
            "concede": i.find("span", class_="concede").string,
            "results": i.find("span", class_="results").string,
            "odds": [j.string for j in i.find("span", class_="odds").find_all("em")]
        }
    )
for i in final_list:
    print i["matchid"], i["hostid"], i["visitid"], i["odds"]