50
51
52
53
54
55
56
57
58
59
60
61
62
63
|
# fetch
html = ""
if search: # pretty much identical (except first page should be /dir/?action=search and POST field)
cat = search
max_pages = 1
for i in range(1, max_pages + 1):
html += ahttp.get("%s/%s/page%s" % (self.base, cat, i))
if not re.search('href="/dir/%s/page%s">Next' % (cat, i + 1), html):
break
# extract
ls = re.findall("""
<tr> .*?
|
>
|
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
|
# fetch
html = ""
if search: # pretty much identical (except first page should be /dir/?action=search and POST field)
cat = search
max_pages = 1
for i in range(1, max_pages + 1):
self.status(i / 12.5)
html += ahttp.get("%s/%s/page%s" % (self.base, cat, i))
if not re.search('href="/dir/%s/page%s">Next' % (cat, i + 1), html):
break
# extract
ls = re.findall("""
<tr> .*?
|