get links of html

XiaomingSu · XiaomingSu · commit df7b416b18c2 · 2015-06-30T15:51:01.000+08:00
diff --git a/PyBeaner/0009/link_in_html.py b/PyBeaner/0009/link_in_html.py
@@ -0,0 +1,22 @@
+# coding=utf-8
+__author__ = 'PyBeaner'
+from bs4 import BeautifulSoup
+
+
+def get_links(html):
+    soup = BeautifulSoup(html)
+    links = []
+    for link in soup.find_all("a"):
+        href = link["href"]
+        if href.startswith("http"):
+            links.append(href)
+    return links
+
+
+if __name__ == '__main__':
+    import requests
+
+    r = requests.get("https://github.com/")
+    html = r.text
+    links = get_links(html)
+    print(links)
