import gzip, io
data = open('pubmed26n1546.xml.gz', 'rb').read()
print(f'File size: {len(data)}')
try:
    decomp = gzip.decompress(data)
    print(f'Valid gzip! Decompressed: {len(decomp)} bytes')
    from lxml import etree
    root = etree.parse(io.BytesIO(decomp)).getroot()
    articles = root.findall('.//PubmedArticle')
    deletes = root.findall('.//DeleteCitation')
    print(f'PubmedArticle: {len(articles)}, DeleteCitation: {len(deletes)}')
except Exception as e:
    print(f'Corrupted: {e}')