You need htmldoc, rst2html, the Python Imaging Libraray, BeautfiulSoup and spoon. The Debian/Ubuntu-packages are called htmldoc, python-docutils, python-imaging and python-beautifulsoup You can get spoon.py http://beautifulspoon.googlecode.com/svn/trunk/spoon.py
To create the pdf files you have to call the script from django_src/docs
Here is an example output: http://henning.cco-ev.de/django/essential.pdf
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 | #!/usr/bin/env python
# -*- coding: utf-8 -*-
import sys
import os
import re
import urllib
from PIL import Image
from spoon import Spoon
CACHE_PATH = os.path.join(os.getcwd(), "djangobook-image-cache")
rst2html_cmd = "rst2html"
htmldoc_cmd = "htmldoc"
books = [
("essential", [
"overview", "install",
"tutorial01", "tutorial02", "tutorial03", "tutorial04",
"faq", "documentation"
]),
("deployment", [
"modpython", "fastcgi"
]),
("reference", [
"django-admin",
"model-api", "db-api", "transactions",
"templates", "templates_python",
"newforms", "forms", "modelforms",
"testing",
"sessions",
"cache",
"i18n",
"middleware",
"settings",
"url_dispatch",
"request_response",
"generic_views",
"authentication",
"shortcuts",
"unicode",
]),
("contrib", [
"add_ons",
"contenttypes",
"csrf",
"databrowse",
"flatpages",
"form_preview",
"redirects",
"sites",
"sitemaps",
"syndication_feeds",
"webdesign"
]),
("solutions", [
"apache_auth",
"static_files",
"email",
"legacy_databases",
"outputting_pdf",
"outputting_csv",
]),
("etc", [
"design_philosophies",
"contributing",
"admin_css",
"api_stability",
])
]
book_template = """\
<html>
<head><title>Django Developer Documentation: %(title)s</title>
<body>
%(html)s
</body>
</html>
"""
title_template = """
<html>
<head><title>Django Developer Documentation: %(title)s</title>
<body>
<!-- ugly html - but looks good as pdf -->
<br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/>
<br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/>
<img src="%(logo)s" width="100%%"><br/><br/>
<table width="100%%" cellpadding="10">
<tr bgcolor="#092e20" ><td><font color="#ffffff" size="+4" face="Arial,Helvetica,Sans Serif">
Django Developer Documentation
</font></td></tr>
<tr><td><b><font size="+5">%(title)s</font></b></td></tr>
</table>
</body>
</html>
"""
chapter_template = """\
<h1><a name="%(filename)s"></a>%(chapter_title)s</h1>
%(chapter)s
"""
if not os.path.exists(CACHE_PATH):
os.makedirs(CACHE_PATH)
def load_image(url):
filename = os.path.join(
CACHE_PATH,
re.sub("\W", "_", url))
if not os.path.exists(filename):
print "* loading %s..." % url,
sys.stdout.flush()
# Thumbnail?
if url.endswith("t.png"):
try:
urllib.urlretrieve(url[:-5] + ".png", filename)
print "done"
return filename
except:
pass
urllib.urlretrieve(url, filename)
print "done"
return filename
def make_pdf(bookname, html):
logo = load_image("http://media.djangoproject.com/img/logos/django-logo-positive.png")
title = bookname.capitalize()
title_html = "%s-title.html" % bookname
open(title_html, "w").write(title_template % vars())
open("%s.html" % bookname, "w").write(book_template % vars())
cmd = htmldoc_cmd + " --numbered -f %(bookname)s.pdf --titlefile %(title_html)s %(bookname)s.html"
os.system(cmd % vars())
complete_html = ""
for bookname, files in books:
html = ""
for filename in files:
print bookname, filename
target = "%s.html" % filename
os.system(rst2html_cmd + " %(filename)s.txt > %(target)s" % vars())
spoon = Spoon(open(target).read())
# Change headings
for hi in range(5, 0, -1):
for i, tag in enumerate(spoon._["h%s" % hi]):
tag["name"] = "h%s" % (hi + 1)
for link in spoon._.a:
href = link["@href"]
if href.startswith("../") and href.endswith("/"):
href = href[3:-1]
if href in files:
href = "#%s" % href
else:
href = "http://www.djangoproject.com/documentation/%s" % href
link["@href"] = href
# Fix embedded images
for img in spoon._.img:
src = img["@src"]
if src.startswith("http"):
img["@src"] = src = load_image(src)
try:
im = Image.open(src)
width = im.size[0]
if width > 400:
img["@width"] = "100%"
if im.format == "PSD":
# yes there are photoshop files called .png on the site :(
print "* converting photoshop file...",
sys.stdout.flush()
im.save(src, "png")
print "done"
except Exception, e:
print e
chapter_title = " ".join([
s.capitalize() for s in re.split("(\d+|[A-Za-z]+)", filename.replace("_", " ")) if s
])
chapter = spoon._.body.inner_html()
html += chapter_template % vars()
complete_html += html
make_pdf(bookname, html)
make_pdf("complete", complete_html)
|
More like this
- Template tag - list punctuation for a list of items by shapiromatron 10 months, 2 weeks ago
- JSONRequestMiddleware adds a .json() method to your HttpRequests by cdcarter 10 months, 3 weeks ago
- Serializer factory with Django Rest Framework by julio 1 year, 5 months ago
- Image compression before saving the new model / work with JPG, PNG by Schleidens 1 year, 6 months ago
- Help text hyperlinks by sa2812 1 year, 6 months ago
Comments
It rocks! The pdfs it created are really nice. Thank you henning.
#
Please login first before commenting.