#!/usr/bin/env python # # Copyright (c) 2008 Claudio Bantaloukas # http://www.rdfm.org/ # # Permission is hereby granted, free of charge, to any person obtaining a copy # of this software and associated documentation files (the "Software"), to deal # in the Software without restriction, including without limitation the rights # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell # copies of the Software, and to permit persons to whom the Software is # furnished to do so, subject to the following conditions: # # The above copyright notice and this permission notice shall be included in # all copies or substantial portions of the Software. # # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN # THE SOFTWARE. """ Utility to convert resources exported from a zope site to blog posts or pages on a wordpress blog. Install python-docutils python-beautifulsoup """ import sys import xmlrpclib import re from datetime import * from xml.dom import minidom from pprint import pprint import codecs class PostatoreException(Exception): pass class Postatore: def __init__(self, thefile, url, login, password, verbose, alwaysconverttext): self.url=url self.login=login self.password=password self.verbose=verbose self.alwaysConvertText=alwaysconverttext self.service = xmlrpclib.Server(self.url) self.inHeader= True self.inDescription=False self.file = thefile def tryHeader(self, line): t=line.split(': ', 1) isheader=(len(t)==2) if isheader: return (isheader, t[0], t[1]) else: return (isheader, line, None) def handleHeader(self, name, attribute): if name=='title' or name=='Title': self.title = attribute if self.verbose: print "Got Title: ", self.title.encode('latin-1') return if name=='Description': self.inDescription = True if self.verbose: print "Got Description line, ignoring following lines until next header" return if name=='creation_date' or name=='Effective_date': datere = re.compile( r'(\d{4})[/-](\d{,2})[/-](\d{,2}) (\d{,2}):(\d{,2}):(\d{,2})') if self.verbose: print "Date line:", attribute, 'exports to' pprint(datere.search(attribute).groups()) year, month, day, hour, minute, seconds = datere.search(attribute).groups() s=year+ month+ day +u"T" +hour+ u":" +minute+ u":"+ seconds self.creation = xmlrpclib.DateTime(s.encode( 'iso-8859-1')) if self.verbose: print "Got Creation Date: ", self.creation, " from string ", attribute return if name=='Content-Type' or name=='Format': self.type = attribute if self.verbose: print "Got Content-Type: ", self.type return def parseHtmlFormat(self): if self.verbose: print "Will parse html format file" from BeautifulSoup import BeautifulSoup it=self.file.read() soup = BeautifulSoup(it) self.title = unicode(soup.html.head.title.string) self.txt = unicode(soup.body.renderContents(), 'utf-8') for meta in soup.findAll('meta'): if meta['name'] and meta['content']: self.handleHeader( meta['name'], unicode(meta['content'])) def convertHtmlContent(self): if self.verbose: print "Will parse html content through beautifulsoup" from BeautifulSoup import BeautifulSoup soup = BeautifulSoup(self.txt) if not soup.body: self.txt = unicode(soup.prettify(), 'utf-8') else: self.txt = unicode(soup.body.renderContents(), 'utf-8') def parseFile(self): firstline=self.file.read(6) if firstline.startswith(""): self.file.seek(0) self.parseHtmlFormat() else: self.file.seek(0) self.parseTextFormat() def parseTextFormat(self): if self.verbose: print "Will parse text format file" self.txt='' for line in self.file: line = line.rstrip('\n').rstrip('\r') (isheader, name, attribute)=self.tryHeader(line) if isheader: if self.inDescription: self.inDescription=False self.handleHeader(name, attribute) if self.inDescription: continue if (self.inHeader): if line=="": self.inHeader = False continue else: self.txt+=line self.txt+='\n' self.handleContent() def handleContent(self): if self.type=="text/plain": if self.alwaysConvertText: self.convertRstContent() return if self.type=="text/html": self.convertHtmlContent() return if self.type=="text/x-rst" or self.type=="text/structured": self.convertRstContent() return raise PostatoreException("Dont know how to handle content-type "+self.type) def convertRstContent(self): from docutils import core, io if self.verbose: print "Will convert ReStructuredText to html before uploading" overrides= { 'input_encoding':'unicode', 'doctitle_xform':1, 'initial_header_level':1 } parts= core.publish_parts( source=self.txt, source_path=None, destination_path=None, writer_name='html', settings_overrides=overrides) self.txt = parts['html_body'] def getPages(self): pprint(self.service.wp.getPages("", self.login, self.password)) def getMethods(self): pprint(self.service.system.listMethods()) def addPage(self, publish): post = {} post['title']=self.title post['description']=self.txt post['dateCreated']=self.creation if self.verbose: print "Will try to add a new page" pprint(post) self.service.wp.newPage('', self.login, self.password, post, publish) def addPost(self, tags, categories, publish): post = {} post['title']=self.title post['description']=self.txt post['dateCreated']=self.creation if tags: post['mt_keywords']=tags.split(',') if categories: post['categories']=categories.split(',') if self.verbose: print "Will try to add a new post" pprint(post) self.service.metaWeblog.newPost('0', self.login, self.password, post, publish) def main(): from optparse import OptionParser parser = OptionParser( usage= 'usage: %prog [OPTION] FILE', description="Extract resources from a zope ftp resource file and post it on a Wordpress blog. The post can be either a wordpress page or a normal post and the original file can be in html or rst format. Categories can be set via a comma separated list. Invalid categories are ignored. The title, date and content are obtained from the zope exported file.") parser.set_defaults(do_page=False) parser.set_defaults(do_post=True) parser.set_defaults(publish=False) parser.set_defaults(alwaysrest=False) parser.add_option('-a', '--page', action="store_true", dest="do_page", help="Turn the zope resource into a Worpress Page") parser.add_option('-o', '--post', action="store_true", dest="do_post", help="Turn the zope resource into a Worpress Post (default action)") parser.add_option('-t', '--tags', dest="tags", help="Add comma separated tags to the post", metavar="TAGS") parser.add_option('-c', '--categories', dest="categories", help="Add the post to a comma separated list of categories", metavar="CATEGORIES") parser.add_option('-i', '--immediately', action='store_true', dest="publish", help="Publish the resulting post or page immediately instead of in draft state") parser.add_option('-r', '--always-rest', action='store_true', dest="alwaysrest", help="Always treat plain text resource as ReStructuredText") parser.add_option('-u', '--username', dest="username", help="Blog username", metavar="USERNAME") parser.add_option('-p', '--password', dest="password", help="Blog password", metavar="PASSWORD") parser.add_option('-U', '--url', dest="url", help="Blog url", metavar="URL") parser.add_option('-v', '--verbose', action='store_true', dest="verbose", help="Increase error and runtime messages", metavar="VERBOSE") (options, args) = parser.parse_args() if not options.url: print "Please provide a blog url" return if not options.username: print "Please provide a blog username" return if not options.password: print "Please provide a blog password" return if len(args) >= 1: file = codecs.open(args[0], 'r', 'utf-8') else: import sys file = sys.stdin fio = Postatore(file, options.url, options.username, options.password, options.verbose, options.alwaysrest) fio.parseFile() #fio.getMethods() #fio.getPages() if options.do_page: fio.addPage(options.publish) else: fio.addPost(options.tags, options.categories, options.publish) if __name__ == '__main__': main()