爬取srtp讲座信息

plough · plough · commit 90418c1447a3 · 2015-12-21T12:34:35.000+08:00
diff --git a/README.md b/README.md
@@ -23,5 +23,8 @@
 ## proxyInfo
 爬取某个代理页面的信息，输出到控制台。
 
+## srtpInfo
+爬取学校网站的srtp讲座信息。
+
 ## tieba
 根据《极客学院》的相关教程实现。使用多线程爬取百度贴吧的帖子信息。涉及到的技术见代码注释。
diff --git a/srtpInfo/srtpSpider.py b/srtpInfo/srtpSpider.py
@@ -0,0 +1,25 @@
+#!/usr/bin/env python
+# encoding: utf-8
+import requests
+from lxml import etree
+import sys
+reload(sys)
+sys.setdefaultencoding('utf-8')
+
+
+def getSrtpInfo():
+    htmlTpl = '<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"></head><body>%s</body></html>'
+    url = 'http://jwc.seu.edu.cn/10097/list.htm'
+
+    html = requests.get(url).content
+    tree = etree.HTML(html.decode('utf-8'))
+    links = [a for a in tree.xpath("//a") if a.text and a.text.startswith("课外研学讲座")]
+    for link in links:
+        print link.text
+        print link.get('href')
+        date = link.getparent().getnext().xpath("div")[0].text
+        print date
+
+
+if __name__ == "__main__":
+    getSrtpInfo()
