"
__copyright__ = "Copyright (C) 2006-2024 PhiloSoft Design"
+from calendar import _localized_month
+import cgi
+import locale
import sys, os
-try:
- from urllib.parse import quote
-except ImportError:
- from urllib import quote
+from urllib.parse import quote, urljoin
from Cheetah.Template import Template
from Cheetah.compat import string_type
+from m_lib.net.www.html import HTMLParser as _HTMLParser
+
+from atom_10 import atom_10
from blog_db import blog_root, load_blog, save_blog
+from news import NewsItem, write_if_changed
+from rss_20 import rss_20
old_blog = load_blog()
@@ -29,59 +34,54 @@ bodies = {}
# Walk the directory recursively
for dirpath, dirs, files in os.walk(blog_root):
- d = os.path.basename(dirpath)
- if not d.startswith("20") and not d.isdigit():
- continue
- for file in files:
- if not file.endswith(".tmpl"):
- continue
- fullpath = os.path.join(dirpath, file)
- template = Template(file=fullpath)
- title_parts = template.Title.decode('utf-8').encode('koi8-r').split()
- title = ' '.join(title_parts[6:])
- lead = template.Lead.decode('utf-8').encode('koi8-r')
-
- tags = template.Tag
- if isinstance(tags, string_type):
- tags = (tags,)
- tags = [tag.decode('utf-8').encode('koi8-r') for tag in tags]
-
- if title:
- key = year, month, day = tuple(dirpath[len(blog_root):].split(os.sep)[1:])
- if key in blog:
- days = blog[key]
- else:
- days = blog[key] = []
- days.append((file, title, lead, tags))
-
- if year in years:
- months = years[year]
- else:
- months = years[year] = {}
-
- if month in months:
- days = months[month]
- else:
- days = months[month] = []
-
- if day not in days: days.append(day)
-
- file = file[:-len("tmpl")] + "html"
- key = (year, month, day, file)
- body = template.body()
- if isinstance(body, unicode):
- body = body.encode('koi8-r')
- bodies[key] = body
+ d = os.path.basename(dirpath)
+ if not d.startswith("20") and not d.isdigit():
+ continue
+ for file in files:
+ if not file.endswith(".tmpl"):
+ continue
+ fullpath = os.path.join(dirpath, file)
+ template = Template(file=fullpath)
+ title_parts = template.Title.split()
+ title = ' '.join(title_parts[6:])
+ lead = template.Lead
+
+ tags = template.Tag
+ if isinstance(tags, string_type):
+ tags = (tags,)
+
+ if title:
+ key = year, month, day = \
+ tuple(dirpath[len(blog_root):].split(os.sep)[1:])
+ if key in blog:
+ days = blog[key]
+ else:
+ days = blog[key] = []
+ days.append((file, title, lead, tags))
+
+ if year in years:
+ months = years[year]
+ else:
+ months = years[year] = {}
+
+ if month in months:
+ days = months[month]
+ else:
+ days = months[month] = []
+
+ if day not in days: days.append(day)
+
+ file = file[:-len("tmpl")] + "html"
+ key = (year, month, day, file)
+ body = template.body()
+ bodies[key] = body
# Need to save the blog?
if blog != old_blog:
save_blog(blog)
# Localized month names
-
-import locale
locale.setlocale(locale.LC_ALL, "ru_RU.KOI8-R")
-from calendar import _localized_month
locale.setlocale(locale.LC_TIME, 'C')
months_names_en = list(_localized_month('%B'))
@@ -90,56 +90,58 @@ months_abbrs_en = list(_localized_month('%b'))
locale.setlocale(locale.LC_TIME, "ru_RU.KOI8-R")
# months_names_ru = list(_localized_month('%B'))
-months_names_ru = ['', "ÑÎ×ÁÒÑ", "ÆÅ×ÒÁÌÑ", "ÍÁÒÔÁ", "ÁÐÒÅÌÑ", "ÍÁÑ", "ÉÀÎÑ",
- "ÉÀÌÑ", "Á×ÇÕÓÔÁ", "ÓÅÎÔÑÂÒÑ", "ÏËÔÑÂÒÑ", "ÎÏÑÂÒÑ", "ÄÅËÁÂÒÑ"
+months_names_ru = [
+ '', "ÑÎ×ÁÒÑ", "ÆÅ×ÒÁÌÑ", "ÍÁÒÔÁ", "ÁÐÒÅÌÑ", "ÍÁÑ", "ÉÀÎÑ",
+ "ÉÀÌÑ", "Á×ÇÕÓÔÁ", "ÓÅÎÔÑÂÒÑ", "ÏËÔÑÂÒÑ", "ÎÏÑÂÒÑ", "ÄÅËÁÂÒÑ"
]
-months_names_ru0 = ['', "ÑÎ×ÁÒØ", "ÆÅ×ÒÁÌØ", "ÍÁÒÔ", "ÁÐÒÅÌØ", "ÍÁÊ", "ÉÀÎØ",
- "ÉÀÌØ", "Á×ÇÕÓÔ", "ÓÅÎÔÑÂÒØ", "ÏËÔÑÂÒØ", "ÎÏÑÂÒØ", "ÄÅËÁÂÒØ"
+months_names_ru0 = [
+ '', "ÑÎ×ÁÒØ", "ÆÅ×ÒÁÌØ", "ÍÁÒÔ", "ÁÐÒÅÌØ", "ÍÁÊ", "ÉÀÎØ",
+ "ÉÀÌØ", "Á×ÇÕÓÔ", "ÓÅÎÔÑÂÒØ", "ÏËÔÑÂÒØ", "ÎÏÑÂÒØ", "ÄÅËÁÂÒØ"
]
-from news import write_if_changed
def encode_tag(tag):
return quote(tag.replace(' ', '_'))
+
def write_template(level, year, month, day, titles, tags=None):
- path = [blog_root]
- if level >= 1:
- path.append(year)
- if level >= 2:
- path.append(month)
- if level == 3:
- path.append(day)
- path.append("index.tmpl")
- index_name = os.path.join(*path)
-
- new_text = ["""\
+ path = [blog_root]
+ if level >= 1:
+ path.append(year)
+ if level >= 2:
+ path.append(month)
+ if level == 3:
+ path.append(day)
+ path.append("index.tmpl")
+ index_name = os.path.join(*path)
+
+ new_text = ["""\
## THIS FILE IS AUTOMATICALLY GENERATED. DO NOT EDIT.
#encoding koi8-r
#extends phd_site
#implements respond
"""]
- if level == 0:
- new_text.append("""\
+ if level == 0:
+ new_text.append("""\
#attr $Title = "Oleg Broytman's blog"
#attr $Description = "Broytman Russian Blog Index Document"
#attr $Copyright = %(cyear)s
#attr $alternates = (("îÏ×ÏÓÔÉ [Atom 1.0] ÔÏÌØËÏ ÚÁÇÏÌÏ×ËÉ", "application/atom+xml", "atom_10_titles.xml"),
- ("îÏ×ÏÓÔÉ [Atom 1.0]", "application/atom+xml", "atom_10.xml"),
- ("îÏ×ÏÓÔÉ [Atom 1.0] ÐÏÌÎÙÅ ÔÅËÓÔÙ", "application/atom+xml", "atom_10_full.xml"),
- ("îÏ×ÏÓÔÉ [RSS 2.0] ÔÏÌØËÏ ÚÁÇÏÌÏ×ËÉ", "application/rss+xml", "rss_20_titles.xml"),
- ("îÏ×ÏÓÔÉ [RSS 2.0]", "application/rss+xml", "rss_20.xml"),
- ("îÏ×ÏÓÔÉ [RSS 2.0] ÐÏÌÎÙÅ ÔÅËÓÔÙ", "application/rss+xml", "rss_20_full.xml"),
+ ("îÏ×ÏÓÔÉ [Atom 1.0]", "application/atom+xml", "atom_10.xml"),
+ ("îÏ×ÏÓÔÉ [Atom 1.0] ÐÏÌÎÙÅ ÔÅËÓÔÙ", "application/atom+xml", "atom_10_full.xml"),
+ ("îÏ×ÏÓÔÉ [RSS 2.0] ÔÏÌØËÏ ÚÁÇÏÌÏ×ËÉ", "application/rss+xml", "rss_20_titles.xml"),
+ ("îÏ×ÏÓÔÉ [RSS 2.0]", "application/rss+xml", "rss_20.xml"),
+ ("îÏ×ÏÓÔÉ [RSS 2.0] ÐÏÌÎÙÅ ÔÅËÓÔÙ", "application/rss+xml", "rss_20_full.xml"),
)
##
#def body_html
öÕÒÎÁÌ
""" % {"cyear": year or 2005})
- elif level == 1:
- new_text.append("""\
+ elif level == 1:
+ new_text.append("""\
#attr $Title = "Oleg Broytman's blog: %(year)s"
#attr $Description = "Broytman Russian Blog %(year)s Index Document"
#attr $Copyright = %(cyear)s
@@ -148,9 +150,9 @@ def write_template(level, year, month, day, titles, tags=None):
öÕÒÎÁÌ: %(year)s
""" % {"year": year, "cyear": year or 2005})
- elif level == 2:
- imonth = int(month)
- new_text.append("""\
+ elif level == 2:
+ imonth = int(month)
+ new_text.append("""\
#attr $Title = "Oleg Broytman's blog: %(month_abbr_en)s %(year)s"
#attr $Description = "Broytman Russian Blog %(month_name_en)s %(year)s Index Document"
#attr $Copyright = %(cyear)s
@@ -158,21 +160,21 @@ def write_template(level, year, month, day, titles, tags=None):
#def body_html
öÕÒÎÁÌ: %(month_name_ru0)s %(year)s
""" % {
- "year": year, "cyear": year or 2005,
- "month_abbr_en": months_abbrs_en[imonth], "month_name_en": months_names_en[imonth],
- "month_name_ru0": months_names_ru0[imonth],
- })
+ "year": year, "cyear": year or 2005,
+ "month_abbr_en": months_abbrs_en[imonth], "month_name_en": months_names_en[imonth],
+ "month_name_ru0": months_names_ru0[imonth],
+ })
- elif level == 3:
- iday = int(day)
- imonth = int(month)
+ elif level == 3:
+ iday = int(day)
+ imonth = int(month)
- if len(titles) == 1:
- new_text.append("""\
+ if len(titles) == 1:
+ new_text.append("""\
#attr $Refresh = "0; URL=%s"
""" % titles[0][3])
- new_text.append("""\
+ new_text.append("""\
#attr $Title = "Oleg Broytman's blog: %(day)d %(month_abbr_en)s %(year)s"
#attr $Description = "Broytman Russian Blog %(day)d %(month_name_en)s %(year)s Index Document"
#attr $Copyright = %(cyear)s
@@ -180,41 +182,41 @@ def write_template(level, year, month, day, titles, tags=None):
#def body_html
öÕÒÎÁÌ: %(day)d %(month_name_ru)s %(year)s
""" % {
- "year": year, "cyear": year or 2005,
- "month_abbr_en": months_abbrs_en[imonth], "month_name_en": months_names_en[imonth],
- "month_name_ru": months_names_ru[imonth],
- "day": iday
- })
-
- save_titles = titles[:]
- titles.reverse()
-
- save_date = None
- for year, month, day, file, title, lead in titles:
- href = []
- if level == 0:
- href.append(year)
- if level <= 1:
- href.append(month)
- if level <= 2:
- href.append(day)
- href.append(file)
- href = '/'.join(href)
- if day[0] == '0': day = day[1:]
- if save_date != (year, month, day):
- if level == 0:
- new_text.append('\n%s %s %s
' % (day, months_names_ru[int(month)], year))
- else:
- new_text.append('\n%s %s
' % (day, months_names_ru[int(month)]))
- save_date = year, month, day
- new_text.append('''
+ "year": year, "cyear": year or 2005,
+ "month_abbr_en": months_abbrs_en[imonth], "month_name_en": months_names_en[imonth],
+ "month_name_ru": months_names_ru[imonth],
+ "day": iday
+ })
+
+ save_titles = titles[:]
+ titles.reverse()
+
+ save_date = None
+ for year, month, day, file, title, lead in titles:
+ href = []
+ if level == 0:
+ href.append(year)
+ if level <= 1:
+ href.append(month)
+ if level <= 2:
+ href.append(day)
+ href.append(file)
+ href = '/'.join(href)
+ if day[0] == '0': day = day[1:]
+ if save_date != (year, month, day):
+ if level == 0:
+ new_text.append('\n%s %s %s
' % (day, months_names_ru[int(month)], year))
+ else:
+ new_text.append('\n%s %s
' % (day, months_names_ru[int(month)]))
+ save_date = year, month, day
+ new_text.append('''
- %s%s.
+ %s%s.
''' % (lead+' ' if lead else '', href, title))
- if level == 0:
- new_text.append("""
+ if level == 0:
+ new_text.append("""
îÏ×ÏÓÔÅ×ÁÑ ÌÅÎÔÁ × ÆÏÒÍÁÔÁÈ
@@ -229,59 +231,59 @@ def write_template(level, year, month, day, titles, tags=None):
""")
- years = {}
- for year, month, day, file, title, lead in save_titles:
- years[year] = True
- new_text.append('''
+ years = {}
+ for year, month, day, file, title, lead in save_titles:
+ years[year] = True
+ new_text.append('''
ôÅÇÉ:
''')
- first_tag = True
- for count, tag, links in all_tags:
- if first_tag:
- first_tag = False
- else:
- new_text.append(' - ')
- new_text.append("""%s (%d)""" % (
- encode_tag(tag), tag, count))
- new_text.append('''
+ first_tag = True
+ for count, tag, links in all_tags:
+ if first_tag:
+ first_tag = False
+ else:
+ new_text.append(' - ')
+ new_text.append("""%s (%d)""" % (
+ encode_tag(tag), tag, count))
+ new_text.append('''
''')
- max_year = int(sorted(years.keys())[-1])
- years = range(max_year, 2005, -1)
+ max_year = int(sorted(years.keys())[-1])
+ years = range(max_year, 2005, -1)
- new_text.append('''
+ new_text.append('''
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 (%d)' % (year, year, year_counts[str(year)]))
- new_text.append('''
+ 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 (%d)' % (year, year, year_counts[str(year)]))
+ new_text.append('''
''')
- new_text.append("""
+ new_text.append("""
öö
""")
- new_text.append("""\
+ new_text.append("""\
#end def
$phd_site.respond(self)
""")
- write_if_changed(index_name, ''.join(new_text))
+ write_if_changed(index_name, ''.join(new_text))
all_tags = {}
@@ -289,43 +291,40 @@ all_titles = []
all_titles_tags = []
for year in sorted(years.keys()):
- year_titles = []
- months = years[year]
- for month in sorted(months.keys()):
- month_titles = []
- for day in sorted(months[month]):
- day_titles = []
- key = year, month, day
- if key in blog:
- for file, title, lead, tags in blog[key]:
- if file.endswith(".tmpl"): file = file[:-len("tmpl")] + "html"
- value = (year, month, day, file, title, lead)
- all_titles_tags.append((year, month, day, file, title, lead, tags))
- all_titles.append(value)
- year_titles.append(value)
- month_titles.append(value)
- day_titles.append(value)
- for tag in tags:
- if tag in all_tags:
- tag_links = all_tags[tag]
- else:
- tag_links = all_tags[tag] = []
- tag_links.append(value)
- write_template(3, year, month, day, day_titles)
- write_template(2, year, month, day, month_titles)
- write_template(1, year, month, day, year_titles)
-
-def by_count_rev_tag_link(t1, t2):
- """Sort all_tags by count in descending order,
- and by tags and links in ascending order
- """
- r = cmp(t1[0], t2[0])
- if r:
- return -r
- return cmp((t1[1], t1[2]), (t2[1], t2[2]))
+ year_titles = []
+ months = years[year]
+ for month in sorted(months.keys()):
+ month_titles = []
+ for day in sorted(months[month]):
+ day_titles = []
+ key = year, month, day
+ if key in blog:
+ for file, title, lead, tags in blog[key]:
+ if file.endswith(".tmpl"): file = file[:-len("tmpl")] + "html"
+ value = (year, month, day, file, title, lead)
+ all_titles_tags.append((year, month, day, file, title, lead, tags))
+ all_titles.append(value)
+ year_titles.append(value)
+ month_titles.append(value)
+ day_titles.append(value)
+ for tag in tags:
+ if tag in all_tags:
+ tag_links = all_tags[tag]
+ else:
+ tag_links = all_tags[tag] = []
+ tag_links.append(value)
+ write_template(3, year, month, day, day_titles)
+ write_template(2, year, month, day, month_titles)
+ write_template(1, year, month, day, year_titles)
+
+def by_count_rev_tag_link(tag):
+ """Sort all_tags by count in descending order,
+ and by tags and links in ascending order
+ """
+ return tag[:3]
all_tags = [(len(links), tag, links) for (tag, links) in all_tags.items()]
-all_tags.sort(by_count_rev_tag_link)
+all_tags.sort(key=by_count_rev_tag_link)
write_template(0, year, month, day, all_titles[-20:], all_tags)
@@ -345,11 +344,11 @@ new_text = ["""\
æÏÒÍÁ ÐÏÉÓËÁ ÐÏÚ×ÏÌÑÅÔ ÉÓËÁÔØ ÓÏÏÂÝÅÎÉÑ × ÂÌÏÇÅ, ÓÏÏÔ×ÅÔÓÔ×ÕÀÝÉÅ ×ÙÒÁÖÅÎÉÀ.
óÉÎÔÁËÓÉÓ ×ÙÒÁÖÅÎÉÑ:
- - ôÅÇ - ÅÓÌÉ ÔÁËÏÊ ÔÅÇ ÓÕÝÅÓÔ×ÕÅÔ, ÐÒÏÉÚÏÊÄ£Ô ÐÅÒÅÎÁÐÒÁ×ÌÅÎÉÅ ÎÁ ÓÔÒÁÎÉÃÕ ÔÅÇÁ.
- - ïÐÅÒÁÔÏÒ '!' (NOT, not) - ÉÝÅÔ ÚÁÐÉÓÉ, × ËÏÔÏÒÙÈ ÎÅÔ ÜÔÏÇÏ ÔÅÇÁ.
- - ïÐÅÒÁÔÏÒ '&' (AND, and) - ÉÝÅÔ ÚÁÐÉÓÉ, × ËÏÔÏÒÙÈ ÅÓÔØ ÏÂÁ ÔÅÇÁ.
- - ïÐÅÒÁÔÏÒ '|' (OR, or) - ÉÝÅÔ ÚÁÐÉÓÉ, × ËÏÔÏÒÙÈ ÅÓÔØ ÌÀÂÙÅ ÉÚ ÔÅÇÏ×.
- - ðÒÉÏÒÉÔÅÔ ÏÐÅÒÁÃÉÊ ÓÔÁÎÄÁÒÔÎÙÊ: NOT > AND > OR. óËÏÂËÉ '()' ÐÏÚ×ÏÌÑÀÔ ÏÂßÅÄÉÎÑÔØ ×ÙÒÁÖÅÎÉÑ.
+ - ôÅÇ - ÅÓÌÉ ÔÁËÏÊ ÔÅÇ ÓÕÝÅÓÔ×ÕÅÔ, ÐÒÏÉÚÏÊÄ£Ô ÐÅÒÅÎÁÐÒÁ×ÌÅÎÉÅ ÎÁ ÓÔÒÁÎÉÃÕ ÔÅÇÁ.
+ - ïÐÅÒÁÔÏÒ '!' (NOT, not) - ÉÝÅÔ ÚÁÐÉÓÉ, × ËÏÔÏÒÙÈ ÎÅÔ ÜÔÏÇÏ ÔÅÇÁ.
+ - ïÐÅÒÁÔÏÒ '&' (AND, and) - ÉÝÅÔ ÚÁÐÉÓÉ, × ËÏÔÏÒÙÈ ÅÓÔØ ÏÂÁ ÔÅÇÁ.
+ - ïÐÅÒÁÔÏÒ '|' (OR, or) - ÉÝÅÔ ÚÁÐÉÓÉ, × ËÏÔÏÒÙÈ ÅÓÔØ ÌÀÂÙÅ ÉÚ ÔÅÇÏ×.
+ - ðÒÉÏÒÉÔÅÔ ÏÐÅÒÁÃÉÊ ÓÔÁÎÄÁÒÔÎÙÊ: NOT > AND > OR. óËÏÂËÉ '()' ÐÏÚ×ÏÌÑÀÔ ÏÂßÅÄÉÎÑÔØ ×ÙÒÁÖÅÎÉÑ.
ðÒÉÍÅÒÙ ×ÙÒÁÖÅÎÉÊ: linux - ÐÒÏÉÚÏÊÄ£Ô ÐÅÒÅÎÁÐÒÁ×ÌÅÎÉÅ
@@ -359,8 +358,8 @@ linux
@@ -368,22 +367,22 @@ linux
"""]
for i, (count, tag, links) in enumerate(all_tags):
- new_text.append("""\
- %s (%d)
+ new_text.append("""\
+ %s (%d)
""" % (encode_tag(tag), tag, count))
- first = all_tags[0][1]
- if i == 0:
- prev = None
- else:
- prev = all_tags[i-1][1]
- if i >= len(all_tags)-1:
- next = None
- else:
- next = all_tags[i+1][1]
- last = all_tags[-1][1]
-
- tag_text = ["""\
+ first = all_tags[0][1]
+ if i == 0:
+ prev = None
+ else:
+ prev = all_tags[i-1][1]
+ if i >= len(all_tags)-1:
+ next = None
+ else:
+ next = all_tags[i+1][1]
+ last = all_tags[-1][1]
+
+ tag_text = ["""\
## THIS FILE IS AUTOMATICALLY GENERATED. DO NOT EDIT.
#encoding koi8-r
#extends phd_site
@@ -392,25 +391,25 @@ for i, (count, tag, links) in enumerate(all_tags):
#attr $Description = "Broytman Russian Blog Tag %s Index Document"
""" % (tag, tag)]
- tag_text.append("""\
+ tag_text.append("""\
#attr $First = "%s"
""" % first)
- if prev:
- tag_text.append("""\
+ if prev:
+ tag_text.append("""\
#attr $Prev = "%s"
""" % prev)
- if next:
- tag_text.append("""\
+ if next:
+ tag_text.append("""\
#attr $Next = "%s"
""" % next)
- tag_text.append("""\
+ tag_text.append("""\
#attr $Last = "%s"
""" % last)
- tag_text.append("""\
+ tag_text.append("""\
#attr $Copyright = 2006
##
#def body_html
@@ -419,25 +418,25 @@ for i, (count, tag, links) in enumerate(all_tags):
""" % tag)
- count = 0
- for year, month, day, filename, title, lead in reversed(links):
- link = "../%s/%s/%s/%s" % (year, month, day, filename)
- item_text = """- %s/%s/%s: %s%s
""" % (link, year, month, day, lead+' ' if lead else '', title)
+ count = 0
+ for year, month, day, filename, title, lead in reversed(links):
+ link = "../%s/%s/%s/%s" % (year, month, day, filename)
+ item_text = """- %s/%s/%s: %s%s
""" % (link, year, month, day, lead+' ' if lead else '', title)
- count += 1
- if count <= 5:
- new_text.append(" - %s
\n" % item_text)
+ count += 1
+ if count <= 5:
+ new_text.append(" - %s
\n" % item_text)
- tag_text.append(" %s\n" % item_text)
+ tag_text.append(" %s\n" % item_text)
- tag_text.append("""\
+ tag_text.append("""\
#end def
$phd_site.respond(self)
""")
- write_if_changed(os.path.join(blog_root, "tags",
- tag.replace(' ', '_') + ".tmpl"),
- ''.join(tag_text))
+ write_if_changed(os.path.join(blog_root, "tags",
+ tag.replace(' ', '_') + ".tmpl"),
+ ''.join(tag_text))
new_text.append("""\
@@ -447,161 +446,142 @@ $phd_site.respond(self)
write_if_changed(os.path.join(blog_root, "tags", "index.tmpl"), ''.join(new_text))
-from HTMLParser import HTMLParseError
-import cgi
-from urlparse import urljoin
-from m_lib.net.www.html import HTMLParser as _HTMLParser
-
class HTMLDone(Exception): pass
class FirstPHTMLParser(_HTMLParser):
- def __init__(self):
- _HTMLParser.__init__(self)
- self.first_p = None
+ def __init__(self):
+ _HTMLParser.__init__(self)
+ self.first_p = None
- def start_p(self, attrs):
- self.accumulator = ''
+ def start_p(self, attrs):
+ self.accumulator = '
'
- def end_p(self):
- self.first_p = self.accumulator + '
'
- raise HTMLDone()
+ def end_p(self):
+ self.first_p = self.accumulator + ''
+ raise HTMLDone()
def get_first_p(body):
- parser = FirstPHTMLParser()
+ parser = FirstPHTMLParser()
- try:
- parser.feed(body)
- except (HTMLParseError, HTMLDone):
- pass
+ try:
+ parser.feed(body)
+ except HTMLDone:
+ pass
- try:
- parser.close()
- except (HTMLParseError, HTMLDone):
- pass
+ try:
+ parser.close()
+ except HTMLDone:
+ pass
- return parser.first_p
+ 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 __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)
+ parser = AbsURLHTMLParser(base)
- try:
- parser.feed(body)
- except HTMLParseError:
- pass
+ try:
+ parser.feed(body)
+ except Exception:
+ pass
- try:
- parser.close()
- except HTMLParseError:
- pass
+ try:
+ parser.close()
+ except Exception:
+ pass
- return parser.accumulator
+ return parser.accumulator
-from atom_10 import atom_10
-from rss_20 import rss_20
-from news import NewsItem
-
if blog_root:
- blog_root_url = blog_root[
- blog_root.find('/htdocs/phdru.name/') + len('/htdocs/phdru.name/'):]
- baseURL = "https://phdru.name/%s/" % blog_root_url
+ blog_root_url = blog_root[
+ blog_root.find('/htdocs/phdru.name/') + len('/htdocs/phdru.name/'):]
+ baseURL = "https://phdru.name/%s/" % blog_root_url
else:
- baseURL = "https://phdru.name/"
+ baseURL = "https://phdru.name/"
items = []
for item in tuple(reversed(all_titles_tags))[:10]:
- year, month, day, file, title, lead, tags = item
- 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+' ' if lead else '', title),
- url_path)
- items.append(item)
- item.baseURL = baseURL
- item.categoryList = [t.decode('koi8-r').encode('utf-8') for t in tags]
- body = bodies[(year, month, day, file)]
- body = absolute_urls(body, baseURL + url_path)
- try:
- body.decode('utf-8')
- except UnicodeDecodeError:
- body = body.decode('koi8-r').encode('utf-8')
- item.body = body
- excerpt = get_first_p(body)
- try:
- excerpt.decode('utf-8')
- except UnicodeDecodeError:
- excerpt = excerpt.decode('koi8-r').encode('utf-8')
- item.excerpt = excerpt
+ year, month, day, file, title, lead, tags = item
+ url_path = "%s/%s/%s/%s" % (year, month, day, file)
+ item = NewsItem(
+ "%s-%s-%s" % (year, month, day),
+ "%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
+ excerpt = get_first_p(body)
+ item.excerpt = excerpt
namespace = {
- "title": "Oleg Broytman's blog",
- "baseURL": baseURL,
- "indexFile": "",
- "description": "",
- "lang": "ru",
- "author": "Oleg Broytman",
- "email": "phd@phdru.name",
- "generator": os.path.basename(sys.argv[0]),
- "posts": items,
+ "title": "Oleg Broytman's blog",
+ "baseURL": baseURL,
+ "indexFile": "",
+ "description": "",
+ "lang": "ru",
+ "author": "Oleg Broytman",
+ "email": "phd@phdru.name",
+ "generator": os.path.basename(sys.argv[0]),
+ "posts": items,
}
# For english dates
locale.setlocale(locale.LC_TIME, 'C')
-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 = unicode(rss_20(searchList=[namespace])).encode('koi8-r')
-write_if_changed(os.path.join(blog_root, "rss_20.xml"), rss_tmpl)
+atom_tmpl = atom_10(searchList=[namespace])
+write_if_changed(os.path.join(blog_root, "atom_10.xml"), str(atom_tmpl))
+rss_tmpl = rss_20(searchList=[namespace])
+write_if_changed(os.path.join(blog_root, "rss_20.xml"), str(rss_tmpl))
for item in items:
item.excerpt = None
-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 = unicode(rss_20(searchList=[namespace])).encode('koi8-r')
-write_if_changed(os.path.join(blog_root, "rss_20_titles.xml"), rss_tmpl)
+atom_tmpl = atom_10(searchList=[namespace])
+write_if_changed(os.path.join(blog_root, "atom_10_titles.xml"), str(atom_tmpl))
+rss_tmpl = rss_20(searchList=[namespace])
+write_if_changed(os.path.join(blog_root, "rss_20_titles.xml"), str(rss_tmpl))
for item in items:
item.content = item.body
-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 = unicode(rss_20(searchList=[namespace])).encode('koi8-r')
-write_if_changed(os.path.join(blog_root, "rss_20_full.xml"), rss_tmpl)
+atom_tmpl = atom_10(searchList=[namespace])
+write_if_changed(os.path.join(blog_root, "atom_10_full.xml"), str(atom_tmpl))
+rss_tmpl = rss_20(searchList=[namespace])
+write_if_changed(os.path.join(blog_root, "rss_20_full.xml"), str(rss_tmpl))
+
+# vim: set ts=8 sts=4 sw=4 et :
diff --git a/remove_old_html.py b/remove_old_html.py
index bbddded..250f827 100755
--- a/remove_old_html.py
+++ b/remove_old_html.py
@@ -1,7 +1,7 @@
-#! /usr/bin/env python
+#! /usr/bin/env python3
__author__ = "Oleg Broytman "
-__copyright__ = "Copyright (C) 2020, 2021 PhiloSoft Design"
+__copyright__ = "Copyright (C) 2020-2024 PhiloSoft Design"
import os
from blog_db import blog_root, load_blog