对分享列表阅读数进行提取

作者: Designer---Leo
来源: 51数据库
2022-08-12

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Date    : 2015-06-01 10:30:06
# @Author  : HG (hg0728@qq.com)
# @Version : 1.0
import urllib2
import re
import os

def getHtml(url):	#获取html源码
    page = urllib2.urlopen(url)
    html = page.read()
    return html

def urlPages(page):		#翻页
	url = 'http://www.oschina.net/code/list/7/python?p=' + str(page)
	heard={'User-Agent':'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'}
	request=urllib2.Request(url,headers=heard)
	return request

def findList(html):		#正则匹配列表
    myItems = re.findall('<li>.*?<h3 class="code_title">.*?<a href="(.*?)" target="_blank" title="(.*?)">.*?</a>.*?</h3>.*?<p class="u">.*?<span class=\'stat\'>(.*?)回/(.*?)阅/(.*?)顶/(.*?)收藏</span>.*?</p>.*?</li>', html, re.S)
    return myItems

for page in range(1, 30):	#抓取的页数
	html = getHtml(urlPages(page))
	items = findList(html)
	for item in items:
		readmax = int(item[3])
		if readmax > 800:	#阅读数
			s = item[0] + ' ' + item[1] + '\n'
			file_object = open('open.txt', 'a')
			file_object.write(s)
			file_object.close()
		else:
			pass

推荐阅读