Find all full image URLs on a page
parent
eefb33991f
commit
c738ec4a6c
@ -1,3 +1,19 @@
|
|||||||
#!/usr/bin/python
|
#!/usr/bin/python
|
||||||
|
|
||||||
# Regex: href="\/\/images\.4chan\.org\/b\/src\/[0-9]+\.jpg"
|
import re, urllib2
|
||||||
|
|
||||||
|
regex = 'href="(\/\/images\.4chan\.org\/b\/src\/[0-9]+\.jpg)"'
|
||||||
|
url = 'http://boards.4chan.org/b/res/400860795'
|
||||||
|
|
||||||
|
page = urllib2.urlopen(url).read()
|
||||||
|
|
||||||
|
search = re.compile(regex)
|
||||||
|
matches = search.finditer(page)
|
||||||
|
|
||||||
|
urls = []
|
||||||
|
|
||||||
|
for match in matches:
|
||||||
|
if match.group(1) not in urls:
|
||||||
|
urls.append(match.group(1))
|
||||||
|
|
||||||
|
print urls
|
||||||
|
Loading…
Reference in New Issue