X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=reindex_blog.py;h=6c2717c3b49695b4f6d7c4f4a6964a7bea210a03;hb=d76c1ae5fc720b4e22057319b8d98478676f9005;hp=a57f1d2e5db28e9225889729f603ae872af7de52;hpb=a024788d10259bae7f6cd138435959167cdce7ce;p=phdru.name%2Fphdru.name.git
diff --git a/reindex_blog.py b/reindex_blog.py
index a57f1d2..6c2717c 100755
--- a/reindex_blog.py
+++ b/reindex_blog.py
@@ -4,7 +4,7 @@
__version__ = "$Revision$"[11:-2]
__revision__ = "$Id$"[5:-2]
__date__ = "$Date$"[7:-2]
-__author__ = "Oleg Broytman
%s%s.
îÏ×ÏÓÔÅ×ÁÑ ÌÅÎÔÁ × ÆÏÒÍÁÔÁÈ
-Atom 1.0 ðÏ ÇÏÄÁÍ:
@@ -273,7 +281,7 @@ def write_template(level, year, month, day, titles, tags=None):
new_text.append("""\
#end def
-$phd_pp_ru.respond(self)
+$phd_site.respond(self)
""")
write_if_changed(index_name, ''.join(new_text))
@@ -326,7 +334,7 @@ write_template(0, year, month, day, all_titles[-20:], all_tags)
new_text = ["""\
## THIS FILE IS AUTOMATICALLY GENERATED. DO NOT EDIT.
-#extends phd_pp_ru
+#extends phd_site
#implements respond
#attr $Title = "Oleg Broytman's blog: tags"
#attr $Description = "Broytman Russian Blog Tags Index Document"
@@ -339,17 +347,49 @@ new_text = ["""\
%s %s
' % (day, months_names_ru[int(month)]))
save_date = year, month, day
- if lead:
- lead = lead + ' '
- else:
- lead = ''
new_text.append('''
-É RSS 2.0
.
+
+Atom 1.0 ÔÏÌØËÏ ÚÁÇÏÌÏ×ËÉ /
+Atom 1.0 /
+Atom 1.0 ÐÏÌÎÙÅ ÔÅËÓÔÙ
+É
+RSS 2.0 ÔÏÌØËÏ ÚÁÇÏÌÏ×ËÉ /
+RSS 2.0 /
+RSS 2.0 ÐÏÌÎÙÅ ÔÅËÓÔÙ.
"""]
-for count, tag, links in all_tags:
+for i, (count, tag, links) in enumerate(all_tags):
new_text.append("""\
-""" % (tag, tag, tag)]
+""" % 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 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 = '' + 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 + 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", @@ -423,7 +529,7 @@ 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, } @@ -435,3 +541,19 @@ atom_tmpl = str(atom_10(searchList=[namespace])) write_if_changed(os.path.join(blog_root, "atom_10.xml"), atom_tmpl) rss_tmpl = str(rss_20(searchList=[namespace])) 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])) +write_if_changed(os.path.join(blog_root, "atom_10_titles.xml"), atom_tmpl) +rss_tmpl = str(rss_20(searchList=[namespace])) +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])) +write_if_changed(os.path.join(blog_root, "atom_10_full.xml"), atom_tmpl) +rss_tmpl = str(rss_20(searchList=[namespace])) +write_if_changed(os.path.join(blog_root, "rss_20_full.xml"), rss_tmpl)