scripts to test ofind dead links in urls provided in binding docstrings.
authorJordi Riera <kender.jr@gmail.com>
Sat, 31 May 2014 11:09:28 +0000 (13:09 +0200)
committerJordi Riera <kender.jr@gmail.com>
Sat, 31 May 2014 11:09:28 +0000 (13:09 +0200)
bindings_url_parser.py [new file with mode: 0644]

diff --git a/bindings_url_parser.py b/bindings_url_parser.py
new file mode 100644 (file)
index 0000000..252fbb7
--- /dev/null
@@ -0,0 +1,33 @@
+""" script to parse the url of bindings and find if the page exists or not """
+import pprint
+import re
+import os
+import requests
+
+__author__ = 'jordiriera'
+
+url_root = 'https://dev.twitter.com'
+reference_line = re.compile(':reference: ({}.*) "'.format(url_root))
+
+
+def parse(filename):
+    dead_links = []
+    with open(filename, 'r') as file_:
+        for line in file_.readlines():
+            res = reference_line.search(line)
+            if res:
+                if not exists(res.group(1)):
+                    dead_links.append(res.group(1))
+
+    return dead_links
+
+
+def exists(path):
+    r = requests.head(path)
+    return r.status_code == requests.codes.ok
+
+
+if __name__ == '__main__':
+    root = os.path.dirname(os.path.abspath(__file__))
+    filename = os.path.join(root, 'tweepy', 'api.py')
+    pprint.pprint(parse(filename))