python 制作自己的新闻_python编写的简单新浪新闻爬虫

(1)下载BeautifulSoup4.x版本，下载地址：http://www.crummy.com/software/BeautifulSoup/bs4/download/

安装：cmd->进入下载的BeautifulSoup文件目录->执行:python setup.py install

(2)创建保存新闻的文件：NewsTitle.txt

(3)运行程序：python getnews.py(程序名)

# -*- coding: utf-8 -*-

import urllib

import os

from bs4 import BeautifulSoup

import sys

reload(sys)

sys.setdefaultencoding("utf-8")

i = 0

j = 0

# list_a = []

# def gettext(href):

# global j,list_a

# page = urllib.urlopen(href).read()

# soup = BeautifulSoup(page,from_encoding="gb18030")

# div = soup.find_all("div",class_="content")

# p_text = div[0].find_all("p")

# for p in p_text:

# fp = file("%s.txt" % list_a[j],"a")

# fp.write(' ')

# fp.write(p.get_text())

# fp.write(" \n")

# j+=1

def gethref(url): #获得所有链接

global i,list_a

fp = file("NewsTitle.txt","w+")

page = urllib.urlopen(url).read()

soup = BeautifulSoup(page,from_encoding="gb18030")

div = soup.find_all("div",class_="ct_t_01")

h1 = div[0].findall("h1")

for lia in h1:

# list_a.append(("%s、" % (i+1))+lia.h3.get_text())

#href = lia.a.get('href')

# 将标题简介和链接有规则的写入文件中

fp.write("%s、" % (i+1))

i+=1

#fp.write("标题：")

fp.write(lia.get_text())

#fp.write("\n 简介：")

#fp.write(lia.p.get_text())

#fp.write("\n 链接：")

#fp.write(lia.a.get("href"))

fp.write("\n")

#gettext(href)

if "__main__"==__name__:

url ="http://news.sina.com.cn/"

gethref(url)

print "All Is OK!"