source code of /sitemap.py.src

Last modified	2023-02-02
Lines	199

Parent directory Download CGIread sitemap Main page

Quick links: HTML XML content lastmod_changefreq main pretty write_sitemap

1. #!/usr/bin/python2

2. # -*- coding: UTF-8 -*-

4. import compressout

5. import os

6. import time

8. import cgitb

9. cgitb.enable()

11. import sitemapdata

13. def lastmod_changefreq(filename, mod_compressout):

14.     changefreq = [

15.         ('hourly',  21600),     # 6 hours

16.         ('daily',   259200),    # 3 days

17.         ('weekly',  1209600),   # 2 weeks

18.         ('monthly', 5184000),   # 60 days

19.         ('yearly',  -1)             # Stop

20.     ]

21.     last_modifed = os.stat(filename).st_mtime

22.     mod_compressout.write_b('    <lastmod>{}</lastmod>\n'.format(

23.         time.strftime('%Y-%m-%d', time.gmtime(last_modifed))

24.     ))

25.     # Use highest frequency that is at most 2/T

26.     # T is the time between the previous change and the next change.

27.     # As the next change has not yet occurred, assume that

28.     # now = previous + T/2, ie. right in the middle.

29.     time_delta = time.time() - last_modifed

30.     changefreq_kw = None

31.     for keyword, limit in changefreq:

32.         if limit/2.0 > time_delta:

33.             break

34.         changefreq_kw = keyword

35.         if limit < 0:

36.             break

37.     mod_compressout.write_b(

38.         '    <changefreq>{}</changefreq>\n'.format(keyword)

39.     )

41. def pretty(text):

42.     text = text.replace('\n', ' ')

43.     while 2*' ' in text:

44.         text = text.replace(2*' ', 1*' ')

45.     text = text.replace('&', '&')

46.     text = text.replace('<', '&lt;')

47.     text = text.replace('>', '>')

48.     return text.strip()

50. def XML():

51.     compressout.write_h('Content-Type: application/xml; charset=UTF-8\n\n')

52.     compressout.write_b('<?xml version="1.0" encoding="UTF-8"?>\n')

53.     compressout.write_b(

54.         '<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"\n'

55.     )

56.     compressout.write_b(

57.         'xmlns:i="http://www.google.com/schemas/sitemap-image/1.1"\n'

58.     )

59.     compressout.write_b(

60.         'xmlns:v="http://www.google.com/schemas/sitemap-video/1.1"\n'

61.     )

62.     compressout.write_b('>\n\n')

63.     # Flatten subsitemaps

64.     for url in sitemapdata.sitemap:

65.         if 'subsitemap' in url:

66.             sitemapdata.sitemap.extend(url['subsitemap'])

67.             del url['subsitemap']

68.     for url in sitemapdata.sitemap:

69.         compressout.write_b('<url>\n')

70.         compressout.write_b('    <loc>{}</loc>\n'.format(

71.             sitemapdata.site + url['URL']

72.         ))

73.         if 'priority' in url:

74.             compressout.write_b('    <priority>{}</priority>\n'.format(

75.                 url['priority']

76.             ))

77.         if 'file' in url:

78.             lastmod_changefreq(url['file'], compressout)

79.         if 'images' in url:

80.             for image in url['images']:

81.                 compressout.write_b('    <i:image>\n')

82.                 compressout.write_b(

83.                     '        <i:loc>{}</i:loc>\n'.format(

84.                         sitemapdata.imgsite + image['URL']

85.                     )

86.                 )

87.                 if 'description' in image:

88.                     compressout.write_b(

89.                         '        <i:caption>{}</i:caption>\n'.format(

90.                             pretty(image['description'])

91.                         )

92.                     )

93.                 # Image license.

94.                 if 'license' in image:

95.                     license = image['license']

96.                 else:

97.                     license = sitemapdata.imglicense

98.                 if license is not None:

99.                     compressout.write_b(

100.                         '        <i:license>{}</i:license>\n'.format(

101.                             license

102.                         )

103.                     )

104.                 compressout.write_b('    </i:image>\n')

105.         if 'videos' in url:

106.             for video in url['videos']:

107.                 compressout.write_b('    <v:video>\n')

108.                 compressout.write_b(

109.                     '        <v:title>{}</v:title>\n'.format(

110.                         video['title']

111.                     )

112.                 )

113.                 if 'content' in video:

114.                     compressout.write_b(

115.                         '        <v:content_loc>{}</v:content_loc>\n'.format(

116.                             video['content']

117.                         )

118.                     )

119.                 if 'player' in video:

120.                     compressout.write_b(

121.                         '        <v:player_loc>{}</v:player_loc>\n'.format(

122.                             video['player']

123.                         )

124.                     )

125.                 compressout.write_b(

126.                     '        <v:description>{}</v:description>\n'.format(

127.                         video['description']

128.                     )

129.                 )

130.                 compressout.write_b(

131.                     '        <v:thumbnail_loc>{}</v:thumbnail_loc>\n'.format(

132.                         video['thumbnail']

133.                     )

134.                 )

135.                 compressout.write_b('    </v:video>\n')

136.         compressout.write_b('</url>\n')

137.     compressout.write_b('\n</urlset>\n')

139. def HTML():

140.     if 'application/xhtml+xml' in os.getenv('HTTP_ACCEPT', ''):

141.         content_type = 'application/xhtml+xml'

142.     else:

143.         content_type = 'text/html'

144.     compressout.write_h('Content-Type: {}; charset=UTF-8\n\n'.format(

145.         content_type

146.     ))

147.     compressout.write_b('''__HTML5NC__''')

148.     compressout.write_b('''

149.         __TITLE__

150.         <meta name="robots" content="noindex, follow"/>

151.     </head>

152.     <body>

153.         __NAVIGATION__

154.         <main><div id="content">

155.             __H1__

156. ''')

157.     def write_sitemap(sitemap):

158.         compressout.write_b('<ul>\n')

159.         for url in sitemap:

160.             compressout.write_b('<li><a href="{}">{}</a>'.format(

161.                 url['URL'].replace('&', '&').replace('"', '"'),

162.                 pretty(url['description'])

163.             ))

164.             if 'subsitemap' in url:

165.                 write_sitemap(url['subsitemap'])

166.             compressout.write_b('</li>\n')

167.         compressout.write_b('</ul>\n')

168.     write_sitemap(sitemapdata.sitemap)

169.     compressout.write_b('''

170.             <h2>Other sitemaps</h2>

171.             <ul>

172.     ''')

173.     for URL, name in sitemapdata.html_sitemaps:

174.         compressout.write_b('<li><a href="{}">{}</a></li>\n'.format(

175.             URL.replace('&', '&').replace('"', '"'),

176.             pretty(name)

177.         ))

178.     compressout.write_b('''

179.             </ul>

180.         </div></main>

181.         __FOOTER__

182.     </body>

183. </html>

184.     ''')

186. def main():

187.     os.chdir(sitemapdata.basedir)

188.     compressout.init()

189.     compressout.write_h('X-Robots-Tag: noindex, follow\n')

190.     query_string = os.getenv('QUERY_STRING')

191.     if query_string == 'xml':

192.         XML()

193.     else:

194.         HTML()

195.     compressout.done()

197. if __name__ == '__main__':

198.     main()