From 5de39c8539773adbbe167a692752fd47421c060a Mon Sep 17 00:00:00 2001
From: Dongliang Mu <mudongliangabcd@gmail.com>
Date: Sat, 17 Mar 2018 09:16:55 -0400
Subject: [PATCH] add one script to check one link is live or not

---
 Scripts/README.md        | 13 +++++++
 Scripts/get_all_links.py | 77 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 90 insertions(+)
 create mode 100644 Scripts/README.md
 create mode 100755 Scripts/get_all_links.py

diff --git a/Scripts/README.md b/Scripts/README.md
new file mode 100644
index 0000000..9cc1ce0
--- /dev/null
+++ b/Scripts/README.md
@@ -0,0 +1,13 @@
+# Scripts
+
+## Description
+
+`get_all_links.py` : justify one link is live or dead with network connection
+
+## Usage
+
+`get_all_links.py` :
+
+```
+./get_all_links.py ../
+```
diff --git a/Scripts/get_all_links.py b/Scripts/get_all_links.py
new file mode 100755
index 0000000..c8fdd79
--- /dev/null
+++ b/Scripts/get_all_links.py
@@ -0,0 +1,77 @@
+#!/usr/bin/env python
+
+from __future__ import print_function
+from socket import timeout
+
+import os
+import sys
+import codecs
+import re
+
+import markdown
+
+try:
+    # compatible for python2
+    from urllib2 import urlopen
+    from urllib2 import HTTPError
+    from urllib2 import URLError
+except ImportError:
+    # compatible for python3
+    from urllib.request import urlopen
+    from urllib.error import HTTPError
+    from urllib.error import URLError
+
+def check_live_url(url):
+
+    result = False
+    try:
+        ret = urlopen(url, timeout=2)
+        result = (ret.code == 200)
+    except HTTPError as e:
+        print(e, file=sys.stderr)
+    except URLError as e:
+        print(e, file=sys.stderr)
+    except timeout as e:
+        print(e, file=sys.stderr)
+    except Exception as e:
+        print(e, file=sys.stderr)
+
+    return result
+
+
+def main(path):
+
+    filenames = []
+    for (dirpath, dnames, fnames) in os.walk(path):
+        for fname in fnames:
+            if fname.endswith('.md'):
+                filenames.append(os.sep.join([dirpath, fname]))
+
+    urls = []
+
+    for filename in filenames:
+        fd = codecs.open(filename, mode="r", encoding="utf-8")
+        for line in fd.readlines():
+            refs = re.findall(r'(?<=<a href=")[^"]*', markdown.markdown(line))
+            for ref in refs:
+                if ref not in urls:
+                    urls.append(ref)
+
+    #print(len(urls))
+
+    for url in urls:
+        if not url.startswith("http"):
+            print("markdown file name: " + url)
+            continue
+        if check_live_url(url):
+            print(url)
+        else:
+            print(url, file=sys.stderr)
+
+
+if __name__ == '__main__':
+
+    if len(sys.argv) == 2:
+        main(sys.argv[1])
+    else:
+        print("Choose one path as argument one")