def get_code(num):
print 'get page...'
url = 'http://www.c.happycodings.com/code_snippets/code%d.html' % num
text = upen(url).read()
print 'got'
code = re.findall('<TEXTAREA[^>]*>(.+?)</TEXTAREA>', text, re.S)
return code[0]
def get_code(num):
print 'get page...'
url = 'http://www.c.happycodings.com/code_snippets/code%d.html' % num
text = upen(url).read()
print 'got'
code = re.findall('<TEXTAREA[^>]*>(.+?)</TEXTAREA>', text, re.S)
return code[0]
def get_code(num):
print "get page..."
url = "http://www.c.happycodings.com/code_snippets/code%d.html" % num
text = upen(url).read()
print "got"
code = re.findall("<TEXTAREA[^>]*>(.+?)</TEXTAREA>", text, re.S)
return code[0]
from urllib import urlopen as upen
import re
base = 'http://etext.library.adelaide.edu.au/f/fitzgerald/f_scott/gatsby/'
from htmlentitydefs import entitydefs, codepoint2name
print entitydefs, codepoint2name[8220]
fail
def conv(x):
x = x.group()
x = int(x[2:-1])
return entitydefs[codepoint2name[x]]
html = upen(base).read()
all = re.findall('\<a href="chapter(\d+)\.html"\>Chapter', html)
print all
reg = '<div[^>]*>(.+?)</div>'
for i in all:
text = upen(base + 'chapter' + i + '.html').read()
main = re.findall(reg, text, re.S)[1]
main = re.sub('<.+?>', '', main).replace('\n\n', '<br><br>')
main = main.replace('\n', ' ').replace('<br><br>', '\n')
main = re.sub('&#\d+;', conv, main)
open('../prog/gatsby/chapter%s.txt' % i, 'w').write(main)
#!/usr/bin/env python
import cgi
import sys
from urllib import urlopen as upen
form = cgi.FieldStorage()
if form.has_key('url'):
print 'Content-type:image/gif\n'
sys.stdout.write(upen(form['url'].value).read())
else:
print 'Content-type:text/html\n'
print 'hi';
#!/usr/bin/env python
import cgi
import sys
from urllib import urlopen as upen
form = cgi.FieldStorage()
if form.has_key('url'):
print 'Content-type:image/gif\n'
sys.stdout.write(upen(form['url'].value).read())
else:
print 'Content-type:text/html\n'
print 'hi'
from urllib import urlopen as upen
import re
base = 'http://etext.library.adelaide.edu.au/f/fitzgerald/f_scott/gatsby/'
from htmlentitydefs import entitydefs,codepoint2name
print entitydefs,codepoint2name[8220]
fail
def conv(x):
x=x.group();
x=int(x[2:-1])
return entitydefs[codepoint2name[x]]
html = upen(base).read()
all = re.findall('\<a href="chapter(\d+)\.html"\>Chapter',html)
print all
reg = '<div[^>]*>(.+?)</div>'
for i in all:
text = upen(base+'chapter'+i+'.html').read()
main = re.findall(reg,text,re.S)[1]
main = re.sub('<.+?>','',main).replace('\n\n','<br><br>')
main = main.replace('\n',' ').replace('<br><br>','\n')
main = re.sub('&#\d+;',conv,main)
open('../prog/gatsby/chapter%s.txt'%i,'w').write(main)
