萬盛學電腦網

 萬盛學電腦網 >> 網絡編程 >> 編程語言綜合 >> python抓取最新博客內容並生成Rss

python抓取最新博客內容並生成Rss

   本文給大家分享的是使用python抓取最新博客內容並生成Rss的代碼,主要用到了PyRSS2Gen方法,非常的簡單實用,有需要的小伙伴可以參考下。

  osc的rss不是全文輸出的,不開心,所以就有了python抓取osc最新博客生成Rss

  ?

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 # -*- 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內容了,希望大家能夠喜歡。

copyright © 萬盛學電腦網 all rights reserved