X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=Robots%2Fbkmk_robot_base.py;h=3fd567cda2f0c232017d910e4a66526efcec9d75;hb=refs%2Ftags%2F5.3.0;hp=2024ab85efd74594eb4700078f19f7e012ae2b78;hpb=39125836fc96da8bd411da9b03bdc14b48eb4e9d;p=bookmarks_db.git diff --git a/Robots/bkmk_robot_base.py b/Robots/bkmk_robot_base.py index 2024ab8..3fd567c 100644 --- a/Robots/bkmk_robot_base.py +++ b/Robots/bkmk_robot_base.py @@ -5,7 +5,7 @@ This file is a part of Bookmarks database and Internet robot. """ __author__ = "Oleg Broytman " -__copyright__ = "Copyright (C) 2000-2023 PhiloSoft Design" +__copyright__ = "Copyright (C) 2000-2024 PhiloSoft Design" __license__ = "GNU GPL" __all__ = ['robot_base', 'get_error'] @@ -24,6 +24,22 @@ from bkmk_objects import Robot from parse_html import parse_html +# Fake headers to pretend this is a real browser +_user_agent = "Mozilla/5.0 (X11; U; Linux 2.6 i686; en)" +" Gecko/20001221 Firefox/2.0.0" +_x_user_agent = "bookmarks_db (Python %d.%d.%d)" % sys.version_info[:3] + +request_headers = { + 'Accept': '*/*', + 'Accept-Language': 'ru,en', + 'Cache-Control': 'max-age=300', + 'Connection': 'close', + 'Referer': '/', + 'User-Agent': _user_agent, + 'X-User-Agent': _x_user_agent, +} + + reloc_dict = { 301: "perm1.", 302: "temp2.", @@ -66,7 +82,10 @@ class robot_base(Robot): url_type, netloc, url_path, query, url_tag = split_results url_host = split_results.hostname - url = "%s://%s%s" % (url_type, url_host, url_path) + if query: + url = "%s://%s%s?%s" % (url_type, url_host, url_path, query) + else: + url = "%s://%s%s" % (url_type, url_host, url_path) error, redirect_code, redirect_to, headers, content = \ self.get(bookmark, url, True) @@ -135,8 +154,13 @@ class robot_base(Robot): break content_stripped = content.strip() if content_stripped and charset: - content_stripped = content_stripped.decode( - charset, 'replace') + try: + content_stripped = content_stripped.decode( + charset, 'replace') + except LookupError: + charset = None + self.log(" unknown charset " + "in Content-Type header") if content_stripped and is_html: parser = parse_html( content_stripped, charset, self.log) @@ -158,9 +182,16 @@ class robot_base(Robot): if icons[icon_url]: bookmark.icon_href = icon_url content_type, bookmark.icon = icons[icon_url] - self.log(" cached icon: %s" % content_type) + self.log(" cached icon : %s" + % content_type) else: - self.log(" cached icon: no icon") + self.log(" cached icon : no icon") + elif icon_url.startswith('data:'): + content_type, icon_data = \ + icon_url[len('data:'):].split(',', 1) + bookmark.icon_href = bookmark.icon = icon_url + self.log(" got data icon : %s" % content_type) + icons[icon_url] = (content_type, icon_url) else: try: _icon_url = icon_url @@ -211,7 +242,7 @@ class robot_base(Robot): bookmark.icon ) else: - self.log(" no icon :" + self.log(" no icon : " "bad content type '%s'" % content_type )