Read http://lesliezhu.github.com/Notes/index.html and gen my blog's RSS feed file.

genrss.py

#!/usr/bin/env python
#-*- coding:utf-8 -*-

import os,sys,re,time

_rss_ = "http://lesliezhu.github.com/rss.xml"
_dirs_ = ["Notes"]              # only RSS Feed 'Notes'


def gen_url(dir=""):
    """get dir and read dir/index.org to filter URL """

    for line in open(dir+"/index.org").readlines():
        if "[[" in line:
            line=line.strip()
            line=re.search("(\..*html)",line).groups(1)[0]
            yield dir+"/"+line
                

def gen_prefix():
    """ RSS XML prefix """

    print '''<?xml version="1.0" encoding="UTF-8" ?>
    <rss version="2.0">
    <channel>
    <title>弘毅 </title>
    <link>http://lesliezhu.github.com/ </link>
    <description>
    <![CDATA[士不可以不弘毅，任重而道远！ ]]>
    </description>
    <language>zh-CN</language>
    <generator>genrss.py rss generator </generator>
    <webMaster><![CDATA[朱春来(Leslie Zhu)]]></webMaster>
    <ttl>120</ttl>
    <image>
    <title><![CDATA[弘毅]]></title>
    <url>http://lesliezhu.github.io/favicon.ico</url>
    <link>http://lesliezhu.github.com</link>
    </image>
    '''

def gen_suffix():
    """ RSS XML suffix"""

    print '''
    </channel>
    </rss>
    '''
    
def gen_item(link="",creator="朱春来(Leslie Zhu)"):
    """ RSS Item from HTML """

    print '''
    <item> 
    <title> %s </title>
    <link> http://lesliezhu.github.com/%s </link>
    <author><![CDATA[%s]]></author>
    <guid isPermaLink="true">http://lesliezhu.github.com/%s</guid>

    ''' % (gen_title(link),link,creator,link)
    
    for tag in gen_category(link):
        print '''
    <category><![CDATA[%s]]></category>''' % tag

    print '''
    <pubDate>%s</pubDate>
    <description><![CDATA[%s]]></description>
    <comments>http://lesliezhu.github.com/%s</comments>
    </item>
    ''' % (gen_pubdate(link),gen_description(link),link)
    

def gen_category(link=""):
    """ Filter Keywords from HTML metadata """

    for line in open(link).readlines():
        if "<meta name=\"keywords\"" in line:
            line = line.strip()
            keywords=re.search("content=\"(.*)\"",line).groups(1)[0]
            break
    if len(keywords) > 0:
        for ch in "\ ,;:、，":
            if ch in keywords:
                return [i.strip() for i in keywords.split(ch)]
    else:
        return ["札记"]



def gen_title(link=""):
    """ Filter Title from HTML metadata """


    for line in open(link).readlines():
        if "<title>" in line:
            line = line.strip()
            title=re.match("<title>(.*)</title>",line).groups(1)[0]
            break
    return title

def gen_pubdate(link=""):
    """ Filter Publish data from HTML metadata>"""

    for line in open(link).readlines():
        if "<meta name=\"generated\"" in line:
            line = line.strip()
            pattern="([0-9][0-9]/[0-9][0-9]/[0-9][0-9][0-9][0-9]|[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9])"
            pubdate=re.search(pattern,line).groups(1)[0]
            break
    if "/" in pubdate:
        pubdate=time.strptime(pubdate, "%m/%d/%Y")
    elif "-" in pubdate:
        pubdate=time.strptime(pubdate, "%Y-%m-%d")
    else:
        pubdate=re.search("([0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9])",link).groups(1)[0]
        pubdate=time.strptime(pubdate, "%Y-%m-%d")
    
    pubdate=time.strftime("%a, %d %b %Y %H:%M:%S +0800",pubdate)
    return pubdate

def gen_description(link=""):
    """ Filter body data of HTML """

    data=open(link).read()
    data=re.search("(<div id=\"content\">.*</div.).*</body>",data.replace('\n','敏敏')).groups()[0].replace('敏敏','\n')
    #data=re.search("(<\?xml.*</html>)",data.replace('\n','敏敏')).groups(1)[0].replace('敏敏','\n')
    for spec in ['&nbsp']:
        data=data.replace(spec,'')
    return data


if __name__ == "__main__":
    gen_prefix()
    for dir in _dirs_:
        for url in gen_url(dir):
            gen_item(url)
    gen_suffix()