Welcome, guest | Sign In | My Account | Store | Cart
NOTE: Recipes have moved! Please visit GitHub.com/activestate/code for the current versions.

Converts Wordpress Export Files (XML) to multiple html files and optionally uses tags and authors to create a directory structure.

Python, 179 lines
  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
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
import string, os, sys, getopt
from xml.dom import minidom


__author__ = 'Luis Rei <luis.rei@gmail.com>'
__homepage__ = 'http://luisrei.com'
__version__ = '1.0'
__date__ = '2008/03/23'


def convert(infile, outdir, authorDirs, categoryDirs):
    """Convert Wordpress Export File to multiple html files.
    
    Keyword arguments:
    infile -- the location of the Wordpress Export File
    outdir -- the directory where the files will be created
    authorDirs -- if true, create different directories for each author
    categoryDirs -- if true, create directories for each category
    
    """
    
    
    # First we parse the XML file into a list of posts.
    # Each post is a dictionary
    
    dom = minidom.parse(infile)

    blog = [] # list that will contain all posts

    for node in dom.getElementsByTagName('item'):
    	post = dict()

    	post["title"] = node.getElementsByTagName('title')[0].firstChild.data
    	post["date"] = node.getElementsByTagName('pubDate')[0].firstChild.data
    	post["author"] = node.getElementsByTagName(
    	                'dc:creator')[0].firstChild.data
    	post["id"] = node.getElementsByTagName('wp:post_id')[0].firstChild.data
    	
    	if node.getElementsByTagName('content:encoded')[0].firstChild != None:
    	    post["text"] = node.getElementsByTagName(
    	                    'content:encoded')[0].firstChild.data
    	else:
    	    post["text"] = ""
    	
    	# wp:attachment_url could be use to download attachments

    	# Get the categories
    	tempCategories = []
    	for subnode in node.getElementsByTagName('category'):
    		 tempCategories.append(subnode.getAttribute('nicename'))
    	categories = [x for x in tempCategories if x != '']
    	post["categories"] = categories 

    	# Add post to the list of all posts
    	blog.append(post)
    	
    
    # Then we create the directories and HTML files from the list of posts.
    
    # The "base" directory
    outdir += "/wordpress/"
    if os.path.exists(outdir) == False:
        os.makedirs(outdir)
    os.chdir(outdir)
    
    for post in blog:
        # The "category" directories
        path = ""
        if authorDirs == True:
            path += post["author"].encode('utf-8') + "/"
        
        # This creates a path for the file in the format
        # category1/category2/category3/file. Note that the category list was
        # sorted.
        
        if categoryDirs == True:
            if (post["categories"] != None):
                path += string.join(post["categories"],"/")

        if os.path.exists(path) == False and path != "":
            os.makedirs(path)
        
        # And finally the file itself
        path = outdir + path
        title = post["title"].encode('utf-8')
        filename = path + "/" + post["id"] + ' - ' + title \
                    + '.html'
        
        # Add a meta tag to specify charset (UTF-8) in the HTML file
        meta = """<META http-equiv="Content-Type" content="text/html; \
        charset=UTF-8">"""
        
        f = open(filename, 'w')
        f.write(meta+"\n")
        
        # Add "HTML header"
        start = "<html>\n<head>\n<title>"+ title +"</title>\n</head>\n<body>\n"
        f.write(start)
        
        # Convert the unicode object to a string that can be written to a file
        # with the proper encoding (UTF-8)
        text = post["text"].encode('utf-8')
        
        # Replace simple newlines with <br/> + newline so that the HTML file
        # represents the original post more accuratelly
        text = text.replace("\n", "<br/>\n")
        
        
        f.write(text)
        
        # Finalize HTML
        end = "\n</body>\n</html>"
        f.write(end)
        
        f.close()

def usage(pname):
    """Displays usage information
    
    keyword arguments:
    pname -- program name (e.g. obtained as argv[0])
    
    """
    
    
    print """python %s [-hac] [-o outdir] infile
    Converts a Wordpress Export File to multiple html files.
    
    Options:
        -h,--help\tDisplays this information.
        -a,--authors\tCreate different directories for each author.
        -c,--categories\tCreate directory structure from post categories.
        -o,--outdir\tSpecify a directory for the output.
        
    Example:
    python %s -c -o ~/TEMP ~/wordpress.2008-03-20.xml
        """ % (pname, pname)


def main(argv):
    outdir = ""
    authors = False
    categories = False
	
    try:
		opts, args = getopt.getopt(
		    argv[1:], "ha:o:c", ["help", "authors", "outdir", "categories"])	
    except getopt.GetoptError, err:
		print str(err)
		usage(argv[0])
		sys.exit(2)
	
    for opt, arg in opts:
		if opt in ("-h", "--help"):
			usage(argv[0])
			sys.exit()
		elif opt in ("-a", "--authors"):
			authors = True
		elif opt in ("-c", "--categories"):
		    categories = True
		elif opt in ("-o", "--outdir"):
		    outdir = arg
		
    infile = "".join(args)
	
    if infile == "":
	    print "Error: Missing Argument: missing wordpress export file."
	    usage(argv[0])
	    sys.exit(3)
	
    if outdir == "":
	    # Use the current directory
	    outdir = os.getcwd()
	
    convert(infile, outdir, authors, categories)
	

if __name__ == "__main__":
	main(sys.argv)

I used this to export my notes out of a wordpress blog (and into evernote.com).

Issues/notes: Currently does not handle images, attachments or comments. Was only tested on MacOS X (10.5) Was not "carefully" developed e.g. poor exception handling, little testing, ...

For getting a Wordpress Export File see http://wordpress.com/blog/2006/06/12/xml-import-export/