sdfdatareader.py

"""sdfdatareader.py

Super fast skimmer over sdf files just to return the data
fields
"""

def sdf(filename):
    input = open(filename, "r")
    data = {}
    for line in input:
        if line.startswith("> <"):
            k = line.rstrip()[3:-1]
            v = []
            line = input.next().strip()
            while line:
                v.append(line)
                line = input.next().strip()
            data[k] = "\n".join(v)
        elif line.startswith("$$$$"):
            yield data
            data = {}

if __name__ == "__main__":
    filename = r"myfile.sdf"
    for mol in sdf(filename):
        data = mol
    print data