def browse(browseUrlObject):
browseUrl = browseUrlObject.url
try:
url = URL(browseUrl)
dom = DOM(url.download())
visited[browseUrl] = 1
try:
for anchor in dom.by_tag("a"):
url = generateUrl(baseUrl, browseUrl, anchor.href)
if url != "":
try:
dict[url].count = dict[url].count + 1
except:
dict[url] = link(browseUrl, 0, url)
except:
pass
except:
del dict[browseUrl]
print browseUrlObject
brokenUrls[browseUrl] = browseUrlObject
pass
if re.search(r"^/", href):
return root + href
if href.startswith("http://") or href.startswith("www."):
return ""
s = baseurl.split("/")
s = baseurl.replace("/" + s.pop(), "/")
return s + "href"
dict = {}
brokenUrls = {}
visited = {}
rootUrl = "http://winzip.com/win/en/index.htm"
baseUrl = "http://winzip.com"
dict[rootUrl] = link(baseUrl, 0, rootUrl)
def browse(browseUrlObject):
browseUrl = browseUrlObject.url
try:
url = URL(browseUrl)
dom = DOM(url.download())
visited[browseUrl] = 1
try:
for anchor in dom.by_tag("a"):
url = generateUrl(baseUrl, browseUrl, anchor.href)
if url != "":
try:
dict[url].count = dict[url].count + 1
except: