osc的rss不是全文输出的,不开心,所以就有了python抓取osc最新博客生成Rss
# -*- coding: utf-8 -*-
from bs4 import BeautifulSoup
import urllib2
import datetime
import time
import PyRSS2Gen
from email.Utils import formatdate
import re
import sys
import os
reload(sys)
sys.setdefaultencoding('utf-8')
class RssSpider():
def __init__(self):
self.myrss = PyRSS2Gen.RSS2(title='OSChina',
link='http://my.oschina.net',
description=str(datetime.date.today()),
pubDate=datetime.datetime.now(),
lastBuildDate = datetime.datetime.now(),
items=[]
)
self.xmlpath=r'/var/www/myrss/oschina.xml'
self.baseurl="http://www.oschina.net/blog"
#if os.path.isfile(self.xmlpath):
#os.remove(self.xmlpath)
def useragent(self,url):
i_headers = {"User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64)
AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1985.125 Safari/537.36",
"Referer": 'http://baidu.com/'}
req = urllib2.Request(url, headers=i_headers)
html = urllib2.urlopen(req).read()
return html
def enterpage(self,url):
pattern = re.compile(r'd{4}Sd{2}Sd{2}sd{2}Sd{2}')
rsp=self.useragent(url)
soup=BeautifulSoup(rsp)
timespan=soup.find('div',{'class':'BlogStat'})
timespan=str(timespan).strip().replace('n','').decode('utf-8')
match=re.search(r'd{4}Sd{2}Sd{2}sd{2}Sd{2}',timespan)
timestr=str(datetime.date.today())
if match:
timestr=match.group()
#print timestr
ititle=soup.title.string
div=soup.find('div',{'class':'BlogContent'})
rss=PyRSS2Gen.RSSItem(
title=ititle,
link=url,
description = str(div),
pubDate = timestr
)
return rss
def getcontent(self):
rsp=self.useragent(self.baseurl)
soup=BeautifulSoup(rsp)
ul=soup.find('div',{'id':'RecentBlogs'})
for li in ul.findAll('li'):
div=li.find('div')
if div is not None:
alink=div.find('a')
if alink is not None:
link=alink.get('href')
print link
html=self.enterpage(link)
self.myrss.items.append(html)
def SaveRssFile(self,filename):
finallxml=self.myrss.to_xml(encoding='utf-8')
file=open(self.xmlpath,'w')
file.writelines(finallxml)
file.close()
if __name__=='__main__':
rssSpider=RssSpider()
rssSpider.getcontent()
rssSpider.SaveRssFile('oschina.xml')
以上所述就是本文的全部内容了,希望大家能够喜欢。
Copyright© 2013-2020
All Rights Reserved 京ICP备2023019179号-8