from HTMLParser import HTMLParser
-entities = {
- "amp": "&",
- "lt": "<",
- "gt": ">",
- "pound": "£",
- "copy": "©",
- "apos": "'",
- "quot": "\"",
- "nbsp": " ",
- }
-
class HTML2Text(HTMLParser):
-
- def __init__(self):
- self.inheadingone = False
- self.inheadingtwo = False
- self.inotherheading = False
- self.inparagraph = True
- self.inblockquote = False
- self.inlink = False
+ entities = {
+ "amp": "&",
+ "lt": "<",
+ "gt": ">",
+ "pound": "£",
+ "copy": "©",
+ "apos": "'",
+ "quot": "\"",
+ "nbsp": " ",
+ }
+
+ blockleveltags = [
+ "h1",
+ "h2",
+ "h3",
+ "h4",
+ "h5",
+ "h6",
+ "pre",
+ "p",
+ "ul",
+ "ol",
+ "dl",
+ "br",
+ ]
+
+ liststarttags = [
+ "ul",
+ "ol",
+ "dl",
+ ]
+
+ cancontainflow = [
+ "div",
+ "li",
+ "dd",
+ "blockquote",
+ ]
+
+ def __init__(self,textwidth=70):
self.text = u''
- self.currentparagraph = u''
- self.headingtext = u''
- self.blockquote = u''
- self.inpre = False
- self.inul = False
- self.initem = False
- self.item = u''
+ self.curdata = u''
+ self.textwidth = textwidth
+ self.opentags = []
+ self.indentlevel = 0
HTMLParser.__init__(self)
def handle_starttag(self, tag, attrs):
- if tag.lower() == "h1":
- self.inheadingone = True
- self.inparagraph = False
- elif tag.lower() == "h2":
- self.inheadingtwo = True
- self.inparagraph = False
- elif tag.lower() in ["h3", "h4", "h5", "h6"]:
- self.inotherheading = True
- self.inparagraph = False
- elif tag.lower() == "a":
- self.inlink = True
- elif tag.lower() == "br":
- self.handle_br()
- elif tag.lower() == "blockquote":
- self.inblockquote = True
- self.text = self.text + u'\n'
- elif tag.lower() == "p":
- if self.text != "":
- self.text = self.text + u'\n\n'
- if self.inparagraph:
- self.text = self.text \
- + u'\n'.join(textwrap.wrap(self.currentparagraph, 70))
- self.currentparagraph = u''
- self.inparagraph = True
- elif tag.lower() == "pre":
- self.text = self.text + "\n"
- self.inpre = True
- self.inparagraph = False
- self.inblockquote = False
- elif tag.lower() == "ul":
- self.item = u''
- self.inul = True
- self.text = self.text + "\n"
- elif tag.lower() == "li" and self.inul:
- if not self.initem:
- self.initem = True
- self.item = u''
- else:
- self.text = self.text \
- + u' * ' \
- + u'\n '.join([a.strip() for a in \
- textwrap.wrap(self.item, 67)]) \
- + u'\n'
- self.item = u''
+ tag_name = tag.lower()
+ if tag_name in self.blockleveltags:
+ # handle starting a new block - unless we're in a block element
+ # that can contain other blocks, we'll assume that we want to close
+ # the container
+ if tag_name == u'br':
+ self.handle_curdata()
+ self.opentags.append(tag_name)
+ self.opentags.pop()
+
+ if len(self.opentags) > 0:
+ self.handle_curdata()
+ self.opentags.pop()
+ self.opentags.append(tag_name)
+ else:
+ self.handle_curdata()
+ self.opentags.append(tag_name)
def handle_startendtag(self, tag, attrs):
- if tag.lower() == "br":
- self.handle_br()
+ if tag.lower() == u'br':
+ self.tags.append(u'br')
+ self.handle_curdata() # just handle the data, don't do anything else
+ self.tags.pop()
- def handle_br(self):
- if self.inparagraph:
- self.text = self.text \
- + u'\n'.join( \
- [a \
- for a in textwrap.wrap( \
- self.currentparagraph, 70) \
- ] \
- ) \
- + u'\n'
- self.currentparagraph = u''
- elif self.inblockquote:
- self.text = self.text \
- + u'\n> ' \
- + u'\n> '.join( \
- [a \
- for a in textwrap.wrap( \
- self.blockquote.encode("utf-8") \
- , 68) \
- ] \
- ) \
- + u'\n'
- self.blockquote = u''
- else:
- self.text = self.text + "\n"
+ def handle_curdata(self):
+ if len(self.opentags) == 0:
+ return
- def handle_endtag(self, tag):
- if tag.lower() == "h1":
- self.inheadingone = False
+ if len(self.curdata) == 0:
+ return
+
+ tag_thats_done = self.opentags[-1]
+
+ if tag_thats_done in self.blockleveltags:
+ newlinerequired = self.text != u''
+ if newlinerequired:
+ self.text = self.text + u'\n\n'
+
+ if tag_thats_done in ["h1", "h2", "h3", "h4", "h5", "h6"]:
+ underline = u''
+ underlinechar = u'='
+ headingtext = self.curdata.encode("utf-8").strip()
+ headingtext = u'\n'.join( \
+ textwrap.wrap(headingtext, self.textwidth))
+
+ if tag_thats_done == u'h2':
+ underlinechar = u'-'
+ elif tag_thats_done != u'h1':
+ underlinechar = u'~'
+
+ if u'\n' in headingtext:
+ underline = underlinechar * self.textwidth
+ else:
+ underline = underlinechar * len(headingtext)
+ self.text = self.text \
+ + headingtext.encode("utf-8") + u'\n' \
+ + underline
+ elif tag_thats_done == "p":
+ paragraph = self.curdata.encode("utf-8").strip()
self.text = self.text \
- + u'\n\n' \
- + self.headingtext.encode("utf-8") \
- + u'\n' \
- + u'=' * len(self.headingtext.encode("utf-8").strip())
- self.headingtext = u''
- elif tag.lower() == "h2":
- self.inheadingtwo = False
+ + u'\n'.join(textwrap.wrap(paragraph, self.textwidth))
+ elif tag_thats_done == "pre":
+ self.text = self.text + self.curdata
+ elif tag_thats_done == "blockquote":
+ quote = self.curdata.encode("utf-8").strip()
self.text = self.text \
- + u'\n\n' \
- + self.headingtext.encode("utf-8") \
- + u'\n' \
- + u'-' * len(self.headingtext.encode("utf-8").strip())
- self.headingtext = u''
- elif tag.lower() in ["h3", "h4", "h5", "h6"]:
- self.inotherheading = False
+ + u'> ' \
+ + u'> '.join(textwrap.wrap(quote, self.textwidth - 2))
+ elif tag_thats_done == "li":
+ item = self.curdata.encode("utf-8").strip()
+ if len(self.text) > 0 and self.text[-1] != u'\n':
+ self.text = self.text + u'\n'
self.text = self.text \
- + u'\n\n' \
- + self.headingtext.encode("utf-8") \
- + u'\n' \
- + u'~' * len(self.headingtext.encode("utf-8").strip())
- self.headingtext = u''
- elif tag.lower() == "p":
+ + u' * ' \
+ + u'\n '.join( \
+ textwrap.wrap(item, self.textwidth - 3))
+ self.curdata = u''
+ elif tag_thats_done == "dt":
+ definition = self.curdata.encode("utf-8").strip()
+ if len(self.text) > 0 and self.text[-1] != u'\n':
+ self.text = self.text + u'\n\n'
+ elif len(self.text) > 0 and self.text[-2] != u'\n':
+ self.text = self.text + u'\n'
+ definition = definition + "::"
self.text = self.text \
- + u'\n'.join(textwrap.wrap( \
- self.currentparagraph, 70) \
- )
- self.inparagraph = False
- self.currentparagraph = u''
- elif tag.lower() == "blockquote":
+ + '\n '.join(
+ textwrap.wrap(definition, self.textwidth - 1))
+ self.curdata = u''
+ elif tag_thats_done == "dd":
+ definition = self.curdata.encode("utf-8").strip()
+ if len(self.text) > 0 and self.text[-1] != u'\n':
+ self.text = self.text + u'\n'
self.text = self.text \
- + u'\n> ' \
- + u'\n> '.join( \
- [a.strip() \
- for a in textwrap.wrap( \
- self.blockquote, 68)] \
- ) \
- + u'\n'
- self.inblockquote = False
- self.blockquote = u''
- elif tag.lower() == "pre":
- self.inpre = False
- elif tag.lower() == "li":
- self.initem = False
- if self.item != "":
+ + ' ' \
+ + '\n '.join( \
+ textwrap.wrap(definition, self.textwidth - 4))
+ self.curdata = u''
+ elif tag_thats_done in self.liststarttags:
+ pass
+ else:
+ # we've got no idea what this tag does, so we'll
+ # make an assumption that we're not going to know later
+ if len(self.curdata) > 0:
self.text = self.text \
- + u' * ' \
- + u'\n '.join( \
- [a.strip() for a in textwrap.wrap(self.item, 67)]) \
- + u'\n'
- self.item = u''
- elif tag.lower() == "ul":
- self.inul = False
+ + u' ... ' \
+ + u'\n ... '.join( \
+ textwrap.wrap(self.curdata, self.textwidth - 5))
+ self.curdata = u''
+
+ if tag_thats_done in self.blockleveltags:
+ self.curdata = u''
+
+ def handle_endtag(self, tag):
+ try:
+ tagindex = self.opentags.index(tag)
+ except:
+ # closing tag we know nothing about.
+ # err. weird.
+ tagindex = 0
+
+ while tagindex < len(self.opentags) \
+ and tag in self.opentags[tagindex+1:]:
+ try:
+ tagindex = self.opentags.index(tag, tagindex+1)
+ except:
+ # well, we don't want to do that then
+ pass
+ if tagindex != len(self.opentags) - 1:
+ # Assuming the data was for the last opened tag first
+ self.handle_curdata()
+ # Now kill the list to be a slice before this tag was opened
+ self.opentags = self.opentags[:tagindex]
def handle_data(self, data):
- if self.inheadingone or self.inheadingtwo or self.inotherheading:
- self.headingtext = self.headingtext \
- + unicode(data, "utf-8").strip() \
- + u' '
- elif self.inblockquote:
- self.blockquote = self.blockquote \
- + unicode(data, "utf-8").strip() \
- + u' '
- elif self.inparagraph:
- self.currentparagraph = self.currentparagraph \
- + unicode(data, "utf-8").strip() \
- + u' '
- elif self.inul and self.initem:
- self.item = self.item + unicode(data, "utf-8")
- elif self.inpre:
- self.text = self.text + unicode(data, "utf-8")
- else:
- self.text = self.text + unicode(data, "utf-8").strip() + u' '
+ self.curdata = self.curdata + unicode(data, "utf-8")
def handle_entityref(self, name):
entity = name
- if entities.has_key(name.lower()):
- entity = entities[name.lower()]
+ if HTML2Text.entities.has_key(name.lower()):
+ entity = HTML2Text.entities[name.lower()]
elif name[0] == "#":
entity = unichr(int(name[1:]))
else:
entity = "&" + name + ";"
- if self.inparagraph:
- self.currentparagraph = self.currentparagraph \
- + unicode(entity, "utf-8")
- elif self.inblockquote:
- self.blockquote = self.blockquote + unicode(entity, "utf-8")
- else:
- self.text = self.text + unicode(entity, "utf-8")
+ self.curdata = self.curdata + unicode(entity, "utf-8")
def gettext(self):
- data = self.text
- if self.inparagraph:
- data = data + "\n".join(textwrap.wrap(self.currentparagraph, 70))
- return data
+ self.handle_curdata()
+ if len(self.text) == 0 or self.text[-1] != u'\n':
+ self.text = self.text + u'\n'
+ self.opentags = []
+ if len(self.text) > 0:
+ while len(self.text) > 1 and self.text[-1] == u'\n':
+ self.text = self.text[:-1]
+ self.text = self.text + u'\n'
+ return self.text
def open_url(method, url):
redirectcount = 0
msg.add_header("Subject", item["title"])
msg.set_default_type("text/plain")
- htmlpart = MIMEText(content.encode("utf-8"), "html", "utf-8")
+ htmlcontent = content.encode("utf-8")
+ htmlcontent = "%s\n\n<p>Item URL: <a href='%s'>%s</a></p>" %( \
+ content, \
+ item["link"], \
+ item["link"] )
+ htmlpart = MIMEText(htmlcontent.encode("utf-8"), "html", "utf-8")
textparser = HTML2Text()
textparser.feed(content.encode("utf-8"))
textcontent = textparser.gettext()
db.close()
feeddb.close()
-# first off, parse the command line arguments
+if __name__ == "__main__":
+ # This only gets executed if we really called the program
+ # first off, parse the command line arguments
-oparser = OptionParser()
-oparser.add_option(
- "-c", "--conf", dest="conf",
- help="location of config file"
- )
-oparser.add_option(
- "-s", "--statedir", dest="statedir",
- help="location of directory to store state in"
- )
+ oparser = OptionParser()
+ oparser.add_option(
+ "-c", "--conf", dest="conf",
+ help="location of config file"
+ )
+ oparser.add_option(
+ "-s", "--statedir", dest="statedir",
+ help="location of directory to store state in"
+ )
-(options, args) = oparser.parse_args()
+ (options, args) = oparser.parse_args()
-# check for the configfile
+ # check for the configfile
-configfile = None
+ configfile = None
-if options.conf != None:
- # does the file exist?
- try:
- os.stat(options.conf)
- configfile = options.conf
- except:
- # should exit here as the specified file doesn't exist
- sys.stderr.write( \
- "Config file %s does not exist. Exiting.\n" %(options.conf,))
- sys.exit(2)
-else:
- # check through the default locations
- try:
- os.stat("%s/.rss2maildir.conf" %(os.environ["HOME"],))
- configfile = "%s/.rss2maildir.conf" %(os.environ["HOME"],)
- except:
+ if options.conf != None:
+ # does the file exist?
try:
- os.stat("/etc/rss2maildir.conf")
- configfile = "/etc/rss2maildir.conf"
+ os.stat(options.conf)
+ configfile = options.conf
except:
- sys.stderr.write("No config file found. Exiting.\n")
+ # should exit here as the specified file doesn't exist
+ sys.stderr.write( \
+ "Config file %s does not exist. Exiting.\n" %(options.conf,))
sys.exit(2)
+ else:
+ # check through the default locations
+ try:
+ os.stat("%s/.rss2maildir.conf" %(os.environ["HOME"],))
+ configfile = "%s/.rss2maildir.conf" %(os.environ["HOME"],)
+ except:
+ try:
+ os.stat("/etc/rss2maildir.conf")
+ configfile = "/etc/rss2maildir.conf"
+ except:
+ sys.stderr.write("No config file found. Exiting.\n")
+ sys.exit(2)
-# Right - if we've got this far, we've got a config file, now for the hard
-# bits...
+ # Right - if we've got this far, we've got a config file, now for the hard
+ # bits...
-scp = SafeConfigParser()
-scp.read(configfile)
+ scp = SafeConfigParser()
+ scp.read(configfile)
-maildir_root = "RSSMaildir"
-state_dir = "state"
+ maildir_root = "RSSMaildir"
+ state_dir = "state"
-if options.statedir != None:
- state_dir = options.statedir
- try:
- mode = os.stat(state_dir)[stat.ST_MODE]
- if not stat.S_ISDIR(mode):
- sys.stderr.write( \
- "State directory (%s) is not a directory\n" %(state_dir))
- sys.exit(1)
- except:
- # try to make the directory
+ if options.statedir != None:
+ state_dir = options.statedir
try:
- os.mkdir(state_dir)
+ mode = os.stat(state_dir)[stat.ST_MODE]
+ if not stat.S_ISDIR(mode):
+ sys.stderr.write( \
+ "State directory (%s) is not a directory\n" %(state_dir))
+ sys.exit(1)
except:
- sys.stderr.write("Couldn't create statedir %s" %(state_dir))
- sys.exit(1)
-elif scp.has_option("general", "state_dir"):
- new_state_dir = scp.get("general", "state_dir")
- try:
- mode = os.stat(state_dir)[stat.ST_MODE]
- if not stat.S_ISDIR(mode):
- sys.stderr.write( \
- "State directory (%s) is not a directory\n" %(state_dir))
- sys.exit(1)
- except:
- # try to create it
+ # try to make the directory
+ try:
+ os.mkdir(state_dir)
+ except:
+ sys.stderr.write("Couldn't create statedir %s" %(state_dir))
+ sys.exit(1)
+ elif scp.has_option("general", "state_dir"):
+ new_state_dir = scp.get("general", "state_dir")
try:
- os.mkdir(new_state_dir)
- state_dir = new_state_dir
+ mode = os.stat(state_dir)[stat.ST_MODE]
+ if not stat.S_ISDIR(mode):
+ sys.stderr.write( \
+ "State directory (%s) is not a directory\n" %(state_dir))
+ sys.exit(1)
except:
- sys.stderr.write( \
- "Couldn't create state directory %s\n" %(new_state_dir))
- sys.exit(1)
-else:
+ # try to create it
+ try:
+ os.mkdir(new_state_dir)
+ state_dir = new_state_dir
+ except:
+ sys.stderr.write( \
+ "Couldn't create state directory %s\n" %(new_state_dir))
+ sys.exit(1)
+ else:
+ try:
+ mode = os.stat(state_dir)[stat.ST_MODE]
+ if not stat.S_ISDIR(mode):
+ sys.stderr.write( \
+ "State directory %s is not a directory\n" %(state_dir))
+ sys.exit(1)
+ except:
+ try:
+ os.mkdir(state_dir)
+ except:
+ sys.stderr.write( \
+ "State directory %s could not be created\n" %(state_dir))
+ sys.exit(1)
+
+ if scp.has_option("general", "maildir_root"):
+ maildir_root = scp.get("general", "maildir_root")
+
try:
- mode = os.stat(state_dir)[stat.ST_MODE]
+ mode = os.stat(maildir_root)[stat.ST_MODE]
if not stat.S_ISDIR(mode):
sys.stderr.write( \
- "State directory %s is not a directory\n" %(state_dir))
+ "Maildir Root %s is not a directory\n" \
+ %(maildir_root))
sys.exit(1)
except:
try:
- os.mkdir(state_dir)
+ os.mkdir(maildir_root)
except:
- sys.stderr.write( \
- "State directory %s could not be created\n" %(state_dir))
+ sys.stderr.write("Couldn't create Maildir Root %s\n" \
+ %(maildir_root))
sys.exit(1)
-if scp.has_option("general", "maildir_root"):
- maildir_root = scp.get("general", "maildir_root")
-
-try:
- mode = os.stat(maildir_root)[stat.ST_MODE]
- if not stat.S_ISDIR(mode):
- sys.stderr.write( \
- "Maildir Root %s is not a directory\n" \
- %(maildir_root))
- sys.exit(1)
-except:
+ feeds = scp.sections()
try:
- os.mkdir(maildir_root)
+ feeds.remove("general")
except:
- sys.stderr.write("Couldn't create Maildir Root %s\n" %(maildir_root))
- sys.exit(1)
-
-feeds = scp.sections()
-try:
- feeds.remove("general")
-except:
- pass
-
-for section in feeds:
- # check if the directory exists
- maildir = None
- try:
- maildir = scp.get(section, "maildir")
- except:
- maildir = section
+ pass
+
+ for section in feeds:
+ # check if the directory exists
+ maildir = None
+ try:
+ maildir = scp.get(section, "maildir")
+ except:
+ maildir = section
- maildir = urllib.urlencode(((section, maildir),)).split("=")[1]
- maildir = os.path.join(maildir_root, maildir)
+ maildir = urllib.urlencode(((section, maildir),)).split("=")[1]
+ maildir = os.path.join(maildir_root, maildir)
- try:
- exists = os.stat(maildir)
- if stat.S_ISDIR(exists[stat.ST_MODE]):
- # check if there's a new, cur and tmp directory
+ try:
+ exists = os.stat(maildir)
+ if stat.S_ISDIR(exists[stat.ST_MODE]):
+ # check if there's a new, cur and tmp directory
+ try:
+ mode = os.stat(os.path.join(maildir, "cur"))[stat.ST_MODE]
+ except:
+ os.mkdir(os.path.join(maildir, "cur"))
+ if not stat.S_ISDIR(mode):
+ sys.stderr.write("Broken maildir: %s\n" %(maildir))
+ try:
+ mode = os.stat(os.path.join(maildir, "tmp"))[stat.ST_MODE]
+ except:
+ os.mkdir(os.path.join(maildir, "tmp"))
+ if not stat.S_ISDIR(mode):
+ sys.stderr.write("Broken maildir: %s\n" %(maildir))
+ try:
+ mode = os.stat(os.path.join(maildir, "new"))[stat.ST_MODE]
+ if not stat.S_ISDIR(mode):
+ sys.stderr.write("Broken maildir: %s\n" %(maildir))
+ except:
+ os.mkdir(os.path.join(maildir, "new"))
+ else:
+ sys.stderr.write("Broken maildir: %s\n" %(maildir))
+ except:
try:
- mode = os.stat(os.path.join(maildir, "cur"))[stat.ST_MODE]
+ os.mkdir(maildir)
except:
- os.mkdir(os.path.join(maildir, "cur"))
- if not stat.S_ISDIR(mode):
- sys.stderr.write("Broken maildir: %s\n" %(maildir))
+ sys.stderr.write("Couldn't create root maildir %s\n" \
+ %(maildir))
+ sys.exit(1)
try:
- mode = os.stat(os.path.join(maildir, "tmp"))[stat.ST_MODE]
- except:
+ os.mkdir(os.path.join(maildir, "new"))
+ os.mkdir(os.path.join(maildir, "cur"))
os.mkdir(os.path.join(maildir, "tmp"))
- if not stat.S_ISDIR(mode):
- sys.stderr.write("Broken maildir: %s\n" %(maildir))
- try:
- mode = os.stat(os.path.join(maildir, "new"))[stat.ST_MODE]
- if not stat.S_ISDIR(mode):
- sys.stderr.write("Broken maildir: %s\n" %(maildir))
except:
- os.mkdir(os.path.join(maildir, "new"))
- else:
- sys.stderr.write("Broken maildir: %s\n" %(maildir))
- except:
- try:
- os.mkdir(maildir)
- except:
- sys.stderr.write("Couldn't create root maildir %s\n" %(maildir))
- sys.exit(1)
- try:
- os.mkdir(os.path.join(maildir, "new"))
- os.mkdir(os.path.join(maildir, "cur"))
- os.mkdir(os.path.join(maildir, "tmp"))
- except:
- sys.stderr.write( \
- "Couldn't create required maildir directories for %s\n" \
- %(section,))
- sys.exit(1)
+ sys.stderr.write( \
+ "Couldn't create required maildir directories for %s\n" \
+ %(section,))
+ sys.exit(1)
- # right - we've got the directories, we've got the section, we know the
- # url... lets play!
+ # right - we've got the directories, we've got the section, we know the
+ # url... lets play!
- parse_and_deliver(maildir, section, state_dir)
+ parse_and_deliver(maildir, section, state_dir)
projects / rss2maildir.git / blobdiff