comparison uniprotxml_downloader.py @ 5:265c35540faa draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/uniprotxml_downloader commit ba0d41c2dc0dbc0a0d3d200f51e67c6598c7e4e9

4:12692567c7f9

    parser.add_option('-i', '--input', dest='input', default=None, help='Tabular file containing a column of NCBI Taxon IDs')
    parser.add_option('-c', '--column', dest='column', type='int', default=0, help='The column (zero-based) in the tabular file that contains Taxon IDs')
    parser.add_option('-t', '--taxon', dest='taxon', action='append', default=[], help='NCBI taxon ID to download')
    parser.add_option('-r', '--reviewed', dest='reviewed', help='Only uniprot reviewed entries')
    parser.add_option('-f', '--format', dest='format', choices=['xml', 'fasta'], default='xml', help='output format')
    parser.add_option('-o', '--output', dest='output', help='file path for the downloaded uniprot xml')
    parser.add_option('-d', '--debug', dest='debug', action='store_true', default=False, help='Turn on wrapper debugging to stderr')
    (options, args) = parser.parse_args()
    taxids = set(options.taxon)
    if options.input:

                fields = line.rstrip('\r\n').split('\t')
                if len(fields) > abs(options.column):
                    taxid = fields[options.column].strip()
                    if taxid:
                        taxids.add(taxid)
    taxon_queries = ['taxonomy:"%s"' % taxid for taxid in taxids]
    taxon_query = ' OR '.join(taxon_queries)
    if options.output:
        dest_path = options.output
    else:
        dest_path = "uniprot_%s.xml" % '_'.join(taxids)
    reviewed = " reviewed:%s" % options.reviewed if options.reviewed else ''
    try:
        url = 'https://www.uniprot.org/uniprot/'
        query = "%s%s" % (taxon_query, reviewed)
        params = {'query': query, 'force': 'yes', 'format': options.format}
        if options.debug:
            print("%s ? %s" % (url, params), file=sys.stderr)
        data = parse.urlencode(params)
        print(f"Retrieving: {url+data}")
        adapter = TimeoutHTTPAdapter(max_retries=retry_strategy)
        http = requests.Session()
        http.mount("https://", adapter)
        response = http.post(url, data=params)
        http.close()
        with open(dest_path, 'w') as fh:
            fh.write(response.text)
        if options.format == 'xml':
            with open(dest_path, 'r') as contents:
                while True:
                    line = contents.readline()
                    if options.debug:

5:265c35540faa

    parser.add_option('-i', '--input', dest='input', default=None, help='Tabular file containing a column of NCBI Taxon IDs')
    parser.add_option('-c', '--column', dest='column', type='int', default=0, help='The column (zero-based) in the tabular file that contains Taxon IDs')
    parser.add_option('-t', '--taxon', dest='taxon', action='append', default=[], help='NCBI taxon ID to download')
    parser.add_option('-r', '--reviewed', dest='reviewed', help='Only uniprot reviewed entries')
    parser.add_option('-f', '--format', dest='format', choices=['xml', 'fasta'], default='xml', help='output format')
    parser.add_option('-k', '--field', dest='field', choices=['taxonomy_name', 'taxonomy_id'], default='taxonomy_name', help='query field')
    parser.add_option('-o', '--output', dest='output', help='file path for the downloaded uniprot xml')
    parser.add_option('-d', '--debug', dest='debug', action='store_true', default=False, help='Turn on wrapper debugging to stderr')
    (options, args) = parser.parse_args()
    taxids = set(options.taxon)
    if options.input:

                fields = line.rstrip('\r\n').split('\t')
                if len(fields) > abs(options.column):
                    taxid = fields[options.column].strip()
                    if taxid:
                        taxids.add(taxid)
    taxon_queries = [f'{options.field}:"{taxid}"' for taxid in taxids]
    taxon_query = ' OR '.join(taxon_queries)
    if options.output:
        dest_path = options.output
    else:
        dest_path = "uniprot_%s.xml" % '_'.join(taxids)
    reviewed = " reviewed:%s" % options.reviewed if options.reviewed else ''
    try:
        url = 'https://rest.uniprot.org/uniprotkb/stream'
        query = "%s%s" % (taxon_query, reviewed)
        params = {'query': query, 'format': options.format}
        if options.debug:
            print("%s ? %s" % (url, params), file=sys.stderr)
        data = parse.urlencode(params)
        print(f"Retrieving: {url}?{data}")
        adapter = TimeoutHTTPAdapter(max_retries=retry_strategy)

        http = requests.Session()
        http.mount("https://", adapter)
        response = http.get(url, params=params)
        http.close()

        if response.status_code != 200:
            exit(f"Request failed with status code {response.status_code}:\n{response.text}")

        with open(dest_path, 'w') as fh:
            fh.write(response.text)

        if options.format == 'xml':
            with open(dest_path, 'r') as contents:
                while True:
                    line = contents.readline()
                    if options.debug: