Code
From Wizardsforge
(Difference between revisions)
| Line 2: | Line 2: | ||
import urllib | import urllib | ||
| - | + | ||
def write_page(url, filename): | def write_page(url, filename): | ||
sock = urllib.urlopen(url) | sock = urllib.urlopen(url) | ||
htmlSource = sock.read() | htmlSource = sock.read() | ||
sock.close() | sock.close() | ||
| - | + | ||
save = open(filename, 'w') | save = open(filename, 'w') | ||
save.write(htmlSource) | save.write(htmlSource) | ||
save.close() | save.close() | ||
| - | + | ||
| - | + | ||
def write_page_list(list, path): | def write_page_list(list, path): | ||
index = open(path+'/index.txt', 'w') | index = open(path+'/index.txt', 'w') | ||
Revision as of 00:53, 13 October 2006
Python code to get a set of pages:
import urllib
def write_page(url, filename):
sock = urllib.urlopen(url)
htmlSource = sock.read()
sock.close()
save = open(filename, 'w')
save.write(htmlSource)
save.close()
def write_page_list(list, path):
index = open(path+'/index.txt', 'w')
for x in range(0, len(list)):
write_page(list[x], path+'/'+str(x)+'.html')
index.write(str(x)+':'+list[x]+'\
')
index.close()
