| 1 |
""" TurboGears offline docs generator |
|---|
| 2 |
|
|---|
| 3 |
TODO: |
|---|
| 4 |
* create folders automatically |
|---|
| 5 |
* replace links to proper link |
|---|
| 6 |
* get css and pic |
|---|
| 7 |
|
|---|
| 8 |
""" |
|---|
| 9 |
import urllib2 |
|---|
| 10 |
import re |
|---|
| 11 |
import os |
|---|
| 12 |
|
|---|
| 13 |
# links |
|---|
| 14 |
acquire_site = "http://docs.turbogears.org/" |
|---|
| 15 |
doclist = "TitleIndex?action=titleindex" |
|---|
| 16 |
|
|---|
| 17 |
# pattern |
|---|
| 18 |
acquire_version = "1.0" |
|---|
| 19 |
comment = "PageCommentData" |
|---|
| 20 |
|
|---|
| 21 |
extra = ["wiki/modern/css/common.css", |
|---|
| 22 |
"wiki/modern/css/screen.css", |
|---|
| 23 |
"wiki/modern/css/print.css", |
|---|
| 24 |
"wiki/modern/css/projection.css"] |
|---|
| 25 |
|
|---|
| 26 |
def get_doclist(): |
|---|
| 27 |
docs = urllib2.urlopen(acquire_site + doclist) |
|---|
| 28 |
targets = [] |
|---|
| 29 |
for link in docs.readlines(): |
|---|
| 30 |
if re.match(acquire_version, link) and (not re.match(comment, link)): |
|---|
| 31 |
targets.append(link) |
|---|
| 32 |
return targets |
|---|
| 33 |
|
|---|
| 34 |
|
|---|
| 35 |
def download_docs(link): |
|---|
| 36 |
""" |
|---|
| 37 |
save targets docs to destination |
|---|
| 38 |
""" |
|---|
| 39 |
#from docutils.core import publish_parts |
|---|
| 40 |
|
|---|
| 41 |
raw = "?action=raw" |
|---|
| 42 |
ext = ".html" |
|---|
| 43 |
|
|---|
| 44 |
link = link.strip() |
|---|
| 45 |
|
|---|
| 46 |
print "download " + acquire_site + link + raw |
|---|
| 47 |
#doc = urllib2.urlopen(acquire_site + link + raw) |
|---|
| 48 |
doc = urllib2.urlopen(acquire_site + link) |
|---|
| 49 |
|
|---|
| 50 |
#outbin = publish_parts(doc.read(),writer_name="html")["html_body"] |
|---|
| 51 |
|
|---|
| 52 |
#prepare_dest() |
|---|
| 53 |
if link == acquire_version: |
|---|
| 54 |
link = "1.0/index" |
|---|
| 55 |
|
|---|
| 56 |
#file path |
|---|
| 57 |
place = os.getcwd() |
|---|
| 58 |
filepath = place+"/"+link+ext |
|---|
| 59 |
filepath.replace('\\', '/') |
|---|
| 60 |
print filepath |
|---|
| 61 |
#open(filepath,'w').write(outbin) |
|---|
| 62 |
open(filepath,'w').write(doc.read()) |
|---|
| 63 |
|
|---|
| 64 |
def process_docs(targets): |
|---|
| 65 |
frontpage = "index" |
|---|
| 66 |
|
|---|
| 67 |
for link in targets: |
|---|
| 68 |
doc = download_docs(link) |
|---|
| 69 |
|
|---|
| 70 |
if __name__ == '__main__': |
|---|
| 71 |
targets = get_doclist() |
|---|
| 72 |
process_docs(targets) |
|---|
| 73 |
|
|---|
