forked from tweepy/tweepy
-
Notifications
You must be signed in to change notification settings - Fork 0
/
bindings_url_parser.py
33 lines (24 loc) · 836 Bytes
/
bindings_url_parser.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
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))