X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=reindex_blog.py;h=33e9077aefd0e6472959c3300d1f105ea59ef6b0;hb=6c0e690c0305f11e55c7ed2ddc6cd71af867b7cf;hp=fd82c1839111ae59ddcd7a7e86eace33d7b9a715;hpb=d68f2dd8fdab1ec22049d14f274ec34a2ed8431f;p=phdru.name%2Fphdru.name.git
diff --git a/reindex_blog.py b/reindex_blog.py
index fd82c18..33e9077 100755
--- a/reindex_blog.py
+++ b/reindex_blog.py
@@ -1,12 +1,8 @@
#! /usr/bin/env python
# -*- coding: koi8-r -*-
-__version__ = "$Revision$"[11:-2]
-__revision__ = "$Id$"[5:-2]
-__date__ = "$Date$"[7:-2]
-__author__ = "Oleg Broytman
%s%s.
ðÏ ÇÏÄÁÍ:
''')
+
+ year_counts = {}
+ for year, month, day, file, title, lead in all_titles:
+ year_counts[year] = 0
+ for year, month, day, file, title, lead in all_titles:
+ year_counts[year] += 1
+
first_year = True
for year in years:
if first_year:
first_year = False
else:
new_text.append(' - ')
- new_text.append('%s' % (year, year))
+ new_text.append('%s (%d)' % (year, year, year_counts[str(year)]))
new_text.append('''
+
+æÏÒÍÁ ÐÏÉÓËÁ ÐÏÚ×ÏÌÑÅÔ ÉÓËÁÔØ ÓÏÏÂÝÅÎÉÑ × ÂÌÏÇÅ, ÓÏÏÔ×ÅÔÓÔ×ÕÀÝÉÅ ×ÙÒÁÖÅÎÉÀ.
+óÉÎÔÁËÓÉÓ ×ÙÒÁÖÅÎÉÑ:
+ðÒÉÍÅÒÙ ×ÙÒÁÖÅÎÉÊ: linux - ÐÒÏÉÚÏÊÄ£Ô ÐÅÒÅÎÁÐÒÁ×ÌÅÎÉÅ
+ÎÁ ÓÔÒÁÎÉÃÕ linux.html; linux&!audio - ÉÓËÁÔØ ÚÁÐÉÓÉ × ËÏÔÏÒÙÈ ÅÓÔØ ÔÅÇ
+linux É ÎÅÔ ÔÅÇÁ audio; linux and not audio - ÔÏ ÖÅ ÓÁÍÏÅ.
+
%s %s
' % (day, months_names_ru[int(month)]))
save_date = year, month, day
- if lead:
- lead = lead + ' '
- else:
- lead = ''
new_text.append('''
ôÅÇÉ
-
+
+
"""]
@@ -371,7 +396,8 @@ for i, (count, tag, links) in enumerate(all_tags):
tag_text = ["""\
## THIS FILE IS AUTOMATICALLY GENERATED. DO NOT EDIT.
-#extends phd_pp_ru
+#encoding koi8-r
+#extends phd_site
#implements respond
#attr $Title = "Oleg Broytman's blog: tag %s"
#attr $Description = "Broytman Russian Blog Tag %s Index Document"
@@ -401,18 +427,13 @@ for i, (count, tag, links) in enumerate(all_tags):
#def body_html
%s
-
""" % tag)
count = 0
for year, month, day, filename, title, lead in reversed(links):
- if lead:
- lead = lead + ' '
- else:
- lead = ''
link = "../%s/%s/%s/%s" % (year, month, day, filename)
- item_text = """
-
' + + def end_p(self): + self.first_p = self.accumulator + '
' + raise HTMLDone() + +def get_first_p(body): + parser = FirstPHTMLParser() + + try: + parser.feed(body) + except (HTMLParseError, HTMLDone): + pass + + try: + parser.close() + except (HTMLParseError, HTMLDone): + pass + + return parser.first_p + + +class AbsURLHTMLParser(_HTMLParser): + def __init__(self, base): + _HTMLParser.__init__(self) + self.base = base + + def start_a(self, attrs): + self.accumulator += '' + + def end_a(self): + self.accumulator += '' + + def start_img(self, attrs): + self.accumulator += '' + + def end_img(self): + pass + +def absolute_urls(body, base): + parser = AbsURLHTMLParser(base) + + try: + parser.feed(body) + except HTMLParseError: + pass + + try: + parser.close() + except HTMLParseError: + pass + + return parser.accumulator + + from atom_10 import atom_10 from rss_20 import rss_20 from news import NewsItem if blog_root: - baseURL = "http://phd.pp.ru/%s/" % blog_root + baseURL = "http://phdru.name/%s/" % blog_root else: - baseURL = "http://phd.pp.ru/" + baseURL = "http://phdru.name/" items = [] for item in tuple(reversed(all_titles_tags))[:10]: year, month, day, file, title, lead, tags = item - if lead: - lead = lead + ' ' - else: - lead = '' + lead = lead.decode('koi8-r').encode('utf-8') + title = title.decode('koi8-r').encode('utf-8') + url_path = "%s/%s/%s/%s" % (year, month, day, file) item = NewsItem( "%s-%s-%s" % (year, month, day), - "%s%s" % (lead, title), - "%s/%s/%s/%s" % (year, month, day, file) - ) + "%s%s" % (lead+' ' if lead else '', title), + url_path) items.append(item) item.baseURL = baseURL item.categoryList = tags - item.excerpt = excerpts[(year, month, day, file)] - item.body = bodies[(year, month, day, file)] + body = bodies[(year, month, day, file)] + body = absolute_urls(body, baseURL + url_path) + item.body = body + item.excerpt = get_first_p(body) namespace = { "title": "Oleg Broytman's blog", @@ -471,7 +573,7 @@ namespace = { "description": "", "lang": "ru", "author": "Oleg Broytman", - "email": "phd@phd.pp.ru", + "email": "phd@phdru.name", "generator": os.path.basename(sys.argv[0]), "posts": items, } @@ -479,23 +581,23 @@ namespace = { # For english dates locale.setlocale(locale.LC_TIME, 'C') -atom_tmpl = str(atom_10(searchList=[namespace])) +atom_tmpl = unicode(atom_10(searchList=[namespace])).encode('koi8-r') write_if_changed(os.path.join(blog_root, "atom_10.xml"), atom_tmpl) -rss_tmpl = str(rss_20(searchList=[namespace])) +rss_tmpl = unicode(rss_20(searchList=[namespace])).encode('koi8-r') write_if_changed(os.path.join(blog_root, "rss_20.xml"), rss_tmpl) for item in items: item.excerpt = None -atom_tmpl = str(atom_10(searchList=[namespace])) +atom_tmpl = unicode(atom_10(searchList=[namespace])).encode('koi8-r') write_if_changed(os.path.join(blog_root, "atom_10_titles.xml"), atom_tmpl) -rss_tmpl = str(rss_20(searchList=[namespace])) +rss_tmpl = unicode(rss_20(searchList=[namespace])).encode('koi8-r') write_if_changed(os.path.join(blog_root, "rss_20_titles.xml"), rss_tmpl) for item in items: item.content = item.body -atom_tmpl = str(atom_10(searchList=[namespace])) +atom_tmpl = unicode(atom_10(searchList=[namespace])).encode('koi8-r') write_if_changed(os.path.join(blog_root, "atom_10_full.xml"), atom_tmpl) -rss_tmpl = str(rss_20(searchList=[namespace])) +rss_tmpl = unicode(rss_20(searchList=[namespace])).encode('koi8-r') write_if_changed(os.path.join(blog_root, "rss_20_full.xml"), rss_tmpl)