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
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
|
# -*- coding: utf-8 -*-
"""
sphinx.linkcheck
~~~~~~~~~~~~~~~~
The CheckExternalLinksBuilder class.
:copyright: 2008 by Georg Brandl, Thomas Lamb.
:license: BSD.
"""
import socket
from os import path
from urllib2 import build_opener, HTTPError
from docutils import nodes
from sphinx.builder import Builder
from sphinx.util.console import purple, red, darkgreen
# create an opener that will simulate a browser user-agent
opener = build_opener()
opener.addheaders = [('User-agent', 'Mozilla/5.0')]
class CheckExternalLinksBuilder(Builder):
"""
Checks for broken external links.
"""
name = 'linkcheck'
def init(self):
self.good = set()
self.broken = {}
self.redirected = {}
# set a timeout for non-responding servers
socket.setdefaulttimeout(5.0)
# create output file
open(path.join(self.outdir, 'output.txt'), 'w').close()
def get_target_uri(self, docname, typ=None):
return ''
def get_outdated_docs(self):
return self.env.found_docs
def prepare_writing(self, docnames):
return
def write_doc(self, docname, doctree):
self.info()
for node in doctree.traverse(nodes.reference):
try:
self.check(node, docname)
except KeyError:
continue
def check(self, node, docname):
uri = node['refuri']
if '#' in uri:
uri = uri.split('#')[0]
if uri in self.good:
return
if uri[0:5] == 'http:' or uri[0:6] == 'https:':
self.info(uri, nonl=1)
lineno = None
while lineno is None and node:
node = node.parent
lineno = node.line
if uri in self.broken:
(r, s) = self.broken[uri]
elif uri in self.redirected:
(r, s) = self.redirected[uri]
else:
(r, s) = self.resolve(uri)
if r == 0:
self.info(' - ' + darkgreen('working'))
self.good.add(uri)
elif r == 2:
self.info(' - ' + red('broken: ') + s)
self.broken[uri] = (r, s)
self.write_entry('broken', docname, lineno, uri + ': ' + s)
else:
self.info(' - ' + purple('redirected') + ' to ' + s)
self.redirected[uri] = (r, s)
self.write_entry('redirected', docname, lineno, uri + ' to ' + s)
elif len(uri) == 0 or uri[0:7] == 'mailto:' or uri[0:4] == 'ftp:':
return
else:
self.info(uri + ' - ' + red('malformed!'))
self.write_entry('malformed', docname, lineno, uri)
return
def write_entry(self, what, docname, line, uri):
output = open(path.join(self.outdir, 'output.txt'), 'a')
output.write("%s:%s: [%s] %s\n" % (self.env.doc2path(docname, None),
line, what, uri))
output.close()
def resolve(self, uri):
try:
f = opener.open(uri)
f.close()
except HTTPError, err:
#if err.code == 403 and uri.startswith('http://en.wikipedia.org/'):
# # Wikipedia blocks requests from urllib User-Agent
# return (0, 0)
return (2, str(err))
except Exception, err:
return (2, str(err))
if f.url.rstrip('/') == uri.rstrip('/'):
return (0, 0)
else:
return (1, f.url)
def finish(self):
return
|
