Python captures the latest blog content and generates Rss

Python captures the latest blog content and generates Rss

This article will share with you how to use python to capture the latest blog content and generate Rss code. It mainly uses the PyRSS2Gen method, which is very simple and practical. If you need it, you can refer to it.

The rss of osc is not output in full text, so it is not happy that python captures the latest osc blog to generate 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 = 'ossina ', 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} 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': 'centblogs '}) For li in ul. findAll ('lil '): 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 ')

The above is all the content of this article. I hope you will like it.