|
@@ -0,0 +1,40 @@
|
|
1
|
+from urllib.request import urlopen
|
|
2
|
+from urllib.parse import urlparse
|
|
3
|
+import re
|
|
4
|
+import sys
|
|
5
|
+
|
|
6
|
+LINK_REGEX = re.compile("<a [^>]*href=['\"]([^\"]+)['\"][^>]*>")
|
|
7
|
+
|
|
8
|
+
|
|
9
|
+class LinkCollector:
|
|
10
|
+
|
|
11
|
+ def __init__(self, url):
|
|
12
|
+ self.url = "http://" + urlparse(url).netloc
|
|
13
|
+ self.collected_links = set()
|
|
14
|
+ self.visited_links = set()
|
|
15
|
+
|
|
16
|
+ def collect_links(self, path="/"):
|
|
17
|
+ full_url = self.url + path
|
|
18
|
+ self.visited_links.add(full_url)
|
|
19
|
+ page = str(urlopen(full_url).read())
|
|
20
|
+ links = LINK_REGEX.findall(page)
|
|
21
|
+ links = {self.normalize_url(path, link) for link in links}
|
|
22
|
+ self.collected_links = links.union(self.collected_links)
|
|
23
|
+ self.unvisited_links = links.difference(self.visited_links)
|
|
24
|
+ for link in self.unvisited_links:
|
|
25
|
+ if link.startswith(self.url):
|
|
26
|
+ self.collect_links(urlparse(link).path)
|
|
27
|
+
|
|
28
|
+ def normalize_url(self, path, link):
|
|
29
|
+ if link.startswith("http://") or link.startswith("https://"):
|
|
30
|
+ return link
|
|
31
|
+ elif link.startswith("/"):
|
|
32
|
+ return self.url + link
|
|
33
|
+ else:
|
|
34
|
+ return self.url + path.rpartition('/')[0] + '/' + link
|
|
35
|
+
|
|
36
|
+if __name__ == "__main__":
|
|
37
|
+ collector = LinkCollector(sys.argv[1])
|
|
38
|
+ collector.collect_links()
|
|
39
|
+ for link in collector.collected_links:
|
|
40
|
+ print(link)
|