parse_committee_meeting_protocols.py 文件源码

def _parse_rtf_protocol(self, committee_id, meeting_id, bucket, protocol_object_name, parts_object_name, text_object_name):
        # currently with the new API - we don't seem to get rtf files anymore
        # it looks like files which used to be rtf are actually doc
        # need to investigate further
        return False
        # rtf_extractor = os.environ.get("RTF_EXTRACTOR_BIN")
        # if rtf_extractor:
        #     with object_storage.temp_download(protocol_object_name) as protocol_filename:
        #         with tempfile.NamedTemporaryFile() as text_filename:
        #             cmd = rtf_extractor + ' ' + protocol_filename + ' ' + text_filename
        #             try:
        #                 subprocess.check_output(cmd, stderr=subprocess.STDOUT, shell=True)
        #                 protocol_text = fs.read(text_filename)
        #                 with CommitteeMeetingProtocol.get_from_text(protocol_text) as protocol:
        #                     self._parse_protocol_parts(parts_filename, protocol)
        #             except subprocess.SubprocessError:
        #                 logging.exception("committee {} meeting {}: failed to parse rtf file, skipping".format(committee_id,
        #                                                                                                        meeting_id))
        #                 return False
        #             return True
        # else:
        #     logging.warning("missing RTF_EXTRACTOR_BIN environment variable, skipping rtf parsing")
        #     return False