File: sitemap.py

package info (click to toggle)
linkchecker 10.6.0-2
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 3,132 kB
  • sloc: python: 13,154; makefile: 134; sh: 71; xml: 36; sql: 20; javascript: 19; php: 2
file content (82 lines) | stat: -rw-r--r-- 2,751 bytes parent folder | download | duplicates (4)
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
# Copyright (C) 2000-2014 Bastian Kleineidam
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License along
# with this program; if not, write to the Free Software Foundation, Inc.,
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
"""
Main functions for link parsing
"""
from xml.parsers.expat import ParserCreate
from xml.parsers.expat import ExpatError
from ..checker.const import WARN_XML_PARSE_ERROR


class XmlTagUrlParser:
    """Parse XML files and find URLs in text content of a tag name."""

    def __init__(self, tag):
        """Initialize the parser."""
        self.tag = tag
        self.parser = ParserCreate()
        self.parser.buffer_text = True
        self.parser.StartElementHandler = self.start_element
        self.parser.EndElementHandler = self.end_element
        self.parser.CharacterDataHandler = self.char_data

    def parse(self, url_data):
        """Parse XML URL data."""
        self.url_data = url_data
        self.in_tag = False
        self.url = ""
        data = url_data.get_raw_content()
        isfinal = True
        try:
            self.parser.Parse(data, isfinal)
        except ExpatError as expaterr:
            self.url_data.add_warning(expaterr.message, tag=WARN_XML_PARSE_ERROR)

    def start_element(self, name, attrs):
        """Set tag status for start element."""
        self.in_tag = name == self.tag
        self.url = ""

    def end_element(self, name):
        """If end tag is our tag, call add_url()."""
        self.in_tag = False
        if name == self.tag:
            self.add_url()

    def add_url(self):
        """Add non-empty URLs to the queue."""
        if self.url:
            self.url_data.add_url(
                self.url,
                line=self.parser.CurrentLineNumber,
                column=self.parser.CurrentColumnNumber,
            )
            self.url = ""

    def char_data(self, data):
        """If inside the wanted tag, append data to URL."""
        if self.in_tag:
            self.url += data


def parse_sitemap(url_data):
    """Parse XML sitemap data."""
    XmlTagUrlParser("loc").parse(url_data)


def parse_sitemapindex(url_data):
    """Parse XML sitemap index data."""
    XmlTagUrlParser("loc").parse(url_data)