python-oxweb/oxweb/aaaarg.py

62 lines
1.9 KiB
Python
Raw Normal View History

2010-02-15 07:08:42 +00:00
# -*- coding: utf-8 -*-
# vi:si:et:sw=4:sts=4:ts=4
import re
import os
import string
from oxlib import cache
from oxlib.html import stripTags, decodeHtml
from oxlib.text import findRe
from oxlib.normalize import canonicalName
import auth
def readUrl(url, data=None, headers=cache.DEFAULT_HEADERS, timeout=cache.cache_timeout, valid=None):
headers = headers.copy()
headers["Cookie"] = auth.get("aaaarg.cookie")
return cache.readUrl(url, data, headers, timeout)
def readUrlUnicode(url, timeout=cache.cache_timeout):
return cache.readUrlUnicode(url, _readUrl=readUrl, timeout=timeout)
def downloadText(id, filename=None):
#FIXME, what about the cache, this keeps all pdfs in oxcache...
url='http://a.aaaarg.org/node/%d/download' % id
data = readUrl(url, timeout=-1)
headers = cache.getHeaders(url, timeout=-1)
if filename:
with open(filename, "w") as f:
f.write(data)
return
return data
def getTextByLetter(letter):
texts = []
url = 'http://a.aaaarg.org/library/%s' % letter
data = readUrlUnicode(url)
txts = re.compile('<li class="author">(.*?)</li><li class="title"><a href="(.*?)">(.*?)</a></li>').findall(data)
author = 'Unknown Author'
for r in txts:
if r[0] != '&nbsp;':
author = r[0]
link = r[1]
id = findRe(link, '/(\d+)')
title = decodeHtml(r[2])
author_foder = canonicalName(author)
author_foder = os.path.join(author_foder[0], author_foder)
2010-02-27 11:48:49 +00:00
filename = os.path.join(author_foder, '%s (aaarg %s).pdf' % (title.replace('/', '_'), id))
2010-02-15 07:08:42 +00:00
texts.append({
'author': author,
'title': title,
'id': id,
'filename': filename,
})
return texts
def getTexts():
texts = []
for letter in string.letters[:26]:
texts += getTextByLetter(letter)
return texts