comparison retrieve_fasta_from_NCBI.py @ 5:c6de5c7b4ae3 draft default tip

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/fetch_fasta_from_ncbi commit 11ca680184135ef39a6c552d9f3cc427a8ed6c4c

4:64f45c5e94a0

import time
import urllib
import urllib2
import httplib
import re


class Eutils:

    def __init__(self, options, logger):

        self.get_count_value()

        # If no UIDs are found exit script
        if self.count > 0:
            self.get_uids_list()
            self.get_sequences()
        else:
            self.logger.info("No UIDs were found. Exiting script.")

    def get_count_value(self):
        """
        just to retrieve Count (number of UIDs)
        Total number of UIDs from the retrieved set to be shown in the XML

                fasta = response.read()
                response.close()
                if ( (response_code != 200) or ("Resource temporarily unavailable" in fasta)
                    or ("Error" in fasta) or (not fasta.startswith(">") ) ):
                    serverTransaction = False
                else:
                    serverTransaction = True
            except urllib2.HTTPError as e:
                serverTransaction = False
                self.logger.info("urlopen error:%s, %s" % (e.code, e.read() ) )

                self.logger.info("urlopen error: Failed to reach a server")
                self.logger.info("Reason :%s" % ( e.reason ) )
            except httplib.IncompleteRead as e:
                serverTransaction = False
                self.logger.info("IncompleteRead error:  %s" % ( e.partial ) )
        fasta = self.sanitiser(self.dbname, fasta) 
        time.sleep(0.1)
        return fasta
        
    def sanitiser(self, db, fastaseq):

                batch = uids_list[start:end]
                if self.epost(self.dbname, ",".join(batch)) != -1:
                    mfasta = ''
                    while not mfasta:
                        self.logger.info("retrieving batch %d" % ((start / batch_size) + 1))
                        mfasta = self.efetch(self.dbname, self.query_key, self.webenv)
                    out.write(mfasta + '\n')


LOG_FORMAT = '%(asctime)s|%(levelname)-8s|%(message)s'
LOG_DATEFMT = '%Y-%m-%d %H:%M:%S'
LOG_LEVELS = ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL']

        kwargs['filename'] = options.logfile
    logging.basicConfig(**kwargs)
    logger = logging.getLogger('data_from_NCBI')
    
    E = Eutils(options, logger)
    E.retrieve()


if __name__ == "__main__":
    __main__()

5:c6de5c7b4ae3

import time
import urllib
import urllib2
import httplib
import re


class QueryException(Exception):
    pass


class Eutils:

    def __init__(self, options, logger):

        self.get_count_value()

        # If no UIDs are found exit script
        if self.count > 0:
            self.get_uids_list()
            try:
                self.get_sequences()
            except QueryException as e:
                self.logger.error("Exiting script.")
                raise e
        else:
            self.logger.error("No UIDs were found. Exiting script.")
            raise Exception("")

    def get_count_value(self):
        """
        just to retrieve Count (number of UIDs)
        Total number of UIDs from the retrieved set to be shown in the XML

                fasta = response.read()
                response.close()
                if ( (response_code != 200) or ("Resource temporarily unavailable" in fasta)
                    or ("Error" in fasta) or (not fasta.startswith(">") ) ):
                    serverTransaction = False
                    if ( response_code != 200 ):
                        self.logger.info("urlopen error: Response code is not 200")
                    elif ( "Resource temporarily unavailable" in fasta ):
                        self.logger.info("Ressource temporarily unavailable")
                    elif ( "Error" in fasta ):
                        self.logger.info("Error in fasta")
                    else:
                        self.logger.info("Fasta doesn't start with '>'")
                else:
                    serverTransaction = True
            except urllib2.HTTPError as e:
                serverTransaction = False
                self.logger.info("urlopen error:%s, %s" % (e.code, e.read() ) )

                self.logger.info("urlopen error: Failed to reach a server")
                self.logger.info("Reason :%s" % ( e.reason ) )
            except httplib.IncompleteRead as e:
                serverTransaction = False
                self.logger.info("IncompleteRead error:  %s" % ( e.partial ) )
            if (counter > 500):
                serverTransaction = True
        if (counter > 500):
            raise QueryException({"message":"500 Server Transaction Trials attempted for this batch. Aborting."})
        fasta = self.sanitiser(self.dbname, fasta) 
        time.sleep(0.1)
        return fasta
        
    def sanitiser(self, db, fastaseq):

                batch = uids_list[start:end]
                if self.epost(self.dbname, ",".join(batch)) != -1:
                    mfasta = ''
                    while not mfasta:
                        self.logger.info("retrieving batch %d" % ((start / batch_size) + 1))
                        try:
                            mfasta = self.efetch(self.dbname, self.query_key, self.webenv)
                            out.write(mfasta + '\n')
                        except QueryException as e:
                            self.logger.error("%s" % e.message)
                            raise e


LOG_FORMAT = '%(asctime)s|%(levelname)-8s|%(message)s'
LOG_DATEFMT = '%Y-%m-%d %H:%M:%S'
LOG_LEVELS = ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL']

        kwargs['filename'] = options.logfile
    logging.basicConfig(**kwargs)
    logger = logging.getLogger('data_from_NCBI')
    
    E = Eutils(options, logger)
    try:
        E.retrieve()
    except Exception as e:
        sys.exit(1)


if __name__ == "__main__":
    __main__()