#!usr/bin/python

import requests
import time
import sys
import os
from bs4 import BeautifulSoup

web_url = r'http://www.cbooo.cn/year?year=2019'  #IRI2012

filepath = os.path.split(os.path.realpath(__file__))[0] + '\\cbooodata.txt'
fid = open(filepath, 'w', encoding='utf-8')

headers = {
    "Host":
    "www.cbooo.cn",
    "User-Agent":
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36"
}

r = requests.get(web_url, headers=headers)
if r.status_code == 200:
    contentHtml = BeautifulSoup(r.text)
    tbcontent = contentHtml.find(name='table', attrs={"id": "tbContent"})
    temptrHtml = tbcontent.contents
    trHtml = list(filter(lambda x: x != "\n", temptrHtml))
    count = 0

    liste = []
    for tr in trHtml:
        count += 1
        if count == 1:
            continue

        temptdcontent = tr.contents
        tdinfo = ""
        tdcontents = list(filter(lambda x: x != "\n", temptdcontent))
        for item in tdcontents:
            tdinfo += BeautifulSoup(item.text).text.replace("\n", "") + ","
        liste.append(tdinfo)
        fid.write(tdinfo + "\n")
    print(liste)

fid.close()


爬虫内容再当前python脚本下的cbooodata.txt文件