Python FeedParser.feed方法代码示例

# 需要导入模块: from email.feedparser import FeedParser [as 别名]
# 或者: from email.feedparser.FeedParser import feed [as 别名]
class mail:
    """Class to filter mail."""
    def __init__(self):
        """Initialise class"""
        # initiate class for feedparser
        self.raw_stream = FeedParser()

        # variables for parsed mail data
        self.raw_data   = ''
        self.raw_msg    = ''
        self.headers    = {}
        self.body    = ''
        self.sender  = ''
        self.to      = ''
        self.subject = ''
        self.date_s  = ''
        self.date_d  = ''

    def feed(self, r1):
        """Read data before parsing."""
        self.raw_data = ''.join(r1) 

    def parse(self):
        """Parse raw data using FeedParser to extract body and headers."""

        # pass raw data to feedparser instance
        self.raw_stream.feed(self.raw_data)

        # close and create a feedparser instance 
        self.raw_msg = self.raw_stream.close()
        # Mail processing
        # sort raw messages to extract variables
        for each_key in self.raw_msg.keys():
            self.headers[each_key] = self.raw_msg.get(each_key)

        # mail related variables
        # Get payload without parsing if it is not multipart
        if self.raw_msg.is_multipart() == False:
            self.body    = h.html_to_text(self.raw_msg.get_payload())
        # If message is multi-part and has both html/text parts,
        # get only the text message
        elif self.raw_msg.get_content_type() == 'multipart/alternative':
            for part in self.raw_msg.walk():
                if h.contains(part.get_content_type(),'text/plain'):
                    self.body =  part.get_payload(decode=True)
            self.body = h.html_to_text(self.body)
        else:
            # If message is multi-part and encoded with base-64, combine plain 
            # text and html text and strip all html tags
            for part in self.raw_msg.walk():
                if h.contains(part.get_content_type(), 'text'):
                    self.body = self.body + part.get_payload(decode=True)
            self.body = h.html_to_text(self.body)

        # Store data into essential variables
        self.sender  = self.headers['From'].lower()
        self.to      = self.headers['To'].lower()
        self.date_s  = self.headers['Date']
        self.date_d = h.c_date(self.date_s)
        self.subject = self.headers['Subject'].lower()

# 需要导入模块: from email.feedparser import FeedParser [as 别名]
# 或者: from email.feedparser.FeedParser import feed [as 别名]
def get_email_message_from_file(filename="notification.email"):
    """Load a mail and parse it into a email.message."""
    email_string = get_string_from_file(filename)
    parser = FeedParser()
    parser.feed(email_string)
    email_message = parser.close()
    return email_message

# 需要导入模块: from email.feedparser import FeedParser [as 别名]
# 或者: from email.feedparser.FeedParser import feed [as 别名]
 def __init__(self, message=None):
     """Initialize a Message instance."""
     feedparser = FeedParser(email.message.Message)
     feedparser._set_headersonly()
     data = message.read(4096)
     feedparser.feed(data)
     self._become_message(feedparser.close())

# 需要导入模块: from email.feedparser import FeedParser [as 别名]
# 或者: from email.feedparser.FeedParser import feed [as 别名]
  def _parse_batch_api_response(self, response):
    """Parses an individual part of the MIME multipart server response.

    Args:
      response: One part of the MIME mutlipart message, string.
    Raises:
      ValueError: if an invalid HTTP header is encountered.
    Returns:
      An instance of GoogleComputeEngineBase.BATCH_RESPONSE named tuple.
    """
    status, payload = response.split('\n', 1)
    split = status.split(None, 2)
    if len(split) > 1:
      status = split[1]
      reason = split[2] if len(split) > 2 else ''
    else:
      raise ValueError('Invalid HTTP server response.')

    parser = FeedParser()
    parser.feed(payload)
    msg = parser.close()
    msg['status'] = status
    http_response = httplib2.Response(msg)
    http_response.reason = reason
    payload = msg.get_payload()
    return GoogleComputeEngineBase.BATCH_RESPONSE(http_response, payload)

# 需要导入模块: from email.feedparser import FeedParser [as 别名]
# 或者: from email.feedparser.FeedParser import feed [as 别名]
 def message_from_response(self, headers, body):
     fp = FeedParser()
     for header, value in headers.iteritems():
         fp.feed("%s: %s\n" % (header, Header(value).encode()))
     fp.feed("\n")
     fp.feed(body)
     response = fp.close()
     return response

# 需要导入模块: from email.feedparser import FeedParser [as 别名]
# 或者: from email.feedparser.FeedParser import feed [as 别名]
  def _send_batch_request(self, requests):
    """Sends a batch of requests to the server and processes the HTTP responses.

    Args:
      requests: List of GoogleComputeEngineBase.API_REQUEST named tuples. Must
        contain <= MAX_BATCH_SIZE elements.

    Raises:
      ValueError: If requests has more than MAX_BATCH_SIZE elements.

    Returns:
      List of GoogleComputeEngineBase.BATCH_RESPONSE named tuples, one for
      each element of request parameter.
    """
    if len(requests) > MAX_BATCH_SIZE:
      raise ValueError('Too many requests provided'
                       '(maximum is {0})'.format(MAX_BATCH_SIZE))

    batch = _BatchApiRequest()
    base = urlparse.urlsplit(self.base_url)
    base_path = base.path.rstrip('/')
    for i, request in enumerate(requests):
      msg = MIMENonMultipart('application', 'http')
      msg.add_header('Content-ID', '<{0}>'.format(i))
      msg.set_payload(self._serialize_batch_api_request(base_path, request))
      batch.attach(msg)

    batch_string = batch.as_string()
    content_type = 'multipart/mixed; boundary="{0}"'.format(
        batch.get_boundary())

    url = urlparse.urlunsplit((base.scheme, base.netloc, 'batch',
                               self._create_url_query(None), None))
    response, data = self._send_request(url, 'POST', batch_string, content_type)

    if response.status >= 300:
      error = gce.GceError(
          message=response.reason, status=response.status)
      return [error] * len(requests)  # Return all errors.
    elif not data:
      error = gce.GceError(
          message='Server returned no data', status=response.status)
      return [error] * len(requests)  # Return all errors.

    # Process successful response.
    data = 'content-type: {0}\r\n\r\n'.format(response['content-type']) + data
    parser = FeedParser()
    parser.feed(data)
    response = parser.close()

    responses = []
    for part in response.get_payload():
      responses.append((
          int(RESPONSE_ID_REGEX.match(part['Content-ID']).group(1)),
          self._parse_batch_api_response(part.get_payload())))

    responses.sort(key=lambda r: r[0])
    return [r[1] for r in responses]

# 需要导入模块: from email.feedparser import FeedParser [as 别名]
# 或者: from email.feedparser.FeedParser import feed [as 别名]
def from_string(data, base, plugin, enabled=False):
    parser = FeedParser(PluginMessage)
    parser.feed(data)
    message = parser.close()
    message.is_new = False
    message.enabled = enabled
    message.plugin = plugin
    message.base = base
    return message

# 需要导入模块: from email.feedparser import FeedParser [as 别名]
# 或者: from email.feedparser.FeedParser import feed [as 别名]
def message_from_string_safe(text):
    'handle failure by email standard library by bypassing StringIO blowup'
    try: # use the standard library by default
        return email.message_from_string(text)
    except UnicodeEncodeError: # code copied from email.parser.Parser.parse()
        feedparser = FeedParser(Message)
        feedparser._set_headersonly()
        feedparser.feed(text)
        return feedparser.close()

# 需要导入模块: from email.feedparser import FeedParser [as 别名]
# 或者: from email.feedparser.FeedParser import feed [as 别名]
 def parse(self, fp, headersonly=False):
     feedparser = FeedParser(self._class, policy=self.policy)
     if headersonly:
         feedparser._set_headersonly()
     while True:
         data = fp.read(8192)
         if not data:
             break
         feedparser.feed(data)
     return feedparser.close()

# 需要导入模块: from email.feedparser import FeedParser [as 别名]
# 或者: from email.feedparser.FeedParser import feed [as 别名]
def load_message(fp):
    """Load message from a file handle.

    Reads data from a file handler and parse it
    to a message object.
    """
    parser = FeedParser()
    for line in fp.readlines():
        parser.feed(line)
    
    return parser.close()

# 需要导入模块: from email.feedparser import FeedParser [as 别名]
# 或者: from email.feedparser.FeedParser import feed [as 别名]
    def parse(self, fp, headersonly=False):
        """Create a message structure from the data in a file.

        Reads all the data from the file and returns the root of the message
        structure.  Optional headersonly is a flag specifying whether to stop
        parsing after reading the headers or not.  The default is False,
        meaning it parses the entire contents of the file.
        """
        feedparser = FeedParser(self._class)
        if headersonly:
            feedparser._set_headersonly()
        while True:
            data = fp.read(8192)
            if not data:
                break
            feedparser.feed(data)
        return feedparser.close()

# 需要导入模块: from email.feedparser import FeedParser [as 别名]
# 或者: from email.feedparser.FeedParser import feed [as 别名]
 def headers_factory(_, fp, *args):
     headers = 0
     feedparser = FeedParser(OldMessage)
     try:
         while True:
             line = to_local(fp.readline(client._MAXLINE + 1))
             if len(line) > client._MAXLINE:
                 ret = OldMessage()
                 ret.status = 'Line too long'
                 return ret
             headers += 1
             if headers > client._MAXHEADERS:
                 raise client.HTTPException("got more than %d headers" % client._MAXHEADERS)
             feedparser.feed(line)
             if line in ('\r\n', '\n', ''):
                 return feedparser.close()
     finally:
         # break the recursive reference chain
         feedparser.__dict__.clear()

# 需要导入模块: from email.feedparser import FeedParser [as 别名]
# 或者: from email.feedparser.FeedParser import feed [as 别名]
    def __break_into_parts(self):

        p = FeedParser()
        for h in self.get_headers_array():
            p.feed(h + "\r\n")
        p.feed("\r\n")
        p.feed(self.__body)
        msg = p.close()
        parts = msg.get_payload()
        return parts

# 需要导入模块: from email.feedparser import FeedParser [as 别名]
# 或者: from email.feedparser.FeedParser import feed [as 别名]
    def _break_into_parts(self):
        p = FeedParser()

        for h in self._response.headers:
            p.feed(h + ':' + self._response.headers[h] + "\r\n")

        p.feed("\r\n")
        p.feed(self.text())

        msg = p.close()

        parts = msg.get_payload()

        return parts

# 需要导入模块: from email.feedparser import FeedParser [as 别名]
# 或者: from email.feedparser.FeedParser import feed [as 别名]
    def _parse (self):
        """Parse the BDF mime structure and record the locations of the binary
        blobs. Sets up various data fields in the BDFData object."""

        feedparser = FeedParser (Message)
        binarychunks = {}
        sizeinfo = None
        headxml = None
        self.fp.seek (0, 0)

        while True:
            data = self.fp.readline ()
            if not data:
                break

            feedparser.feed (data)

            skip = (data == '\n' and
                    len (feedparser._msgstack) == 3 and
                    feedparser._msgstack[-1].get_content_type () in ('application/octet-stream',
                                                                     'binary/octet-stream'))
            if skip:
                # We just finished reading the headers for a huge binary blob.
                # Time to remember where the data chunk is and pretend it doesn't
                # exist.
                msg = feedparser._msgstack[-1]
                ident = msg['Content-Location']
                assert ident.endswith ('.bin'), 'confusion #1 in hacky MIME parsing!'
                binarychunks[ident] = self.fp.tell ()
                if sizeinfo is None:
                    headxml, sizeinfo, tagpfx = _extract_size_info (feedparser)
                kind = ident.split ('/')[-1]
                assert kind in sizeinfo, 'no size info for binary chunk kind %s in MIME!' % kind
                self.fp.seek (sizeinfo[kind] + 1, 1) # skip ahead by data chunk size
                sample = self.fp.read (16)
                assert sample.startswith ('--MIME'), 'crap, unexpected chunk size in MIME parsing: %r' % sample
                self.fp.seek (-16, 1) # go back

            # check that two major kinds of data are read at least once
            if any([k.split('/')[3] == '3' for k in binarychunks.iterkeys()]):
                break

        if headxml is None:
            raise RuntimeError ('never found any binary data')

        self.mimemsg = feedparser.close ()
        self.headxml = headxml
        self.sizeinfo = sizeinfo
        self.binarychunks = binarychunks

        headsize, intsize = self.calc_intsize()

        # Compute some miscellaneous parameters that we'll need.
#        self.n_integrations = len (self.mimemsg.get_payload ()) - 1
        self.n_integrations = os.stat(self.fp.name).st_size/intsize
        self.n_antennas = int (headxml.find (tagpfx + nanttag).text)
        self.n_baselines = (self.n_antennas * (self.n_antennas - 1)) // 2

        ds = headxml.find (tagpfx + dstag)
        nbb = 0
        nspw = 0
        nchan = 0
        crosspolstr = None

        for bb in ds.findall (tagpfx + basebandtag):
            nbb += 1

            for spw in bb.getchildren ():
                nspw += 1
                nchan += int (spw.get ('numSpectralPoint'))

                if crosspolstr is None:
                    crosspolstr = spw.get ('crossPolProducts')
                elif spw.get ('crossPolProducts') != crosspolstr:
                    raise Exception ('can only handle spectral windows with identical cross pol products')

        self.n_basebands = nbb
        self.n_spws = nspw
        self.n_channels = nchan
        self.crosspols = crosspolstr.split ()
        self.n_pols = len(self.crosspols)

        # if bdf info pkl not present, write it
        if os.path.exists(os.path.dirname(self.pklname)) and self.pklname and (not os.path.exists(self.pklname)):
            logger.info('Writing bdf pkl info to %s...' % (self.pklname))
            with open(self.pklname,'wb') as pkl:
                # Compute some miscellaneous parameters that we'll need.
                pickle.dump( (self.mimemsg, self.headxml, self.sizeinfo, self.binarychunks, self.n_integrations, self.n_antennas, self.n_baselines, self.n_basebands, self.n_spws, self.n_channels, self.crosspols), pkl)

        return self # convenience