Searches Sanger's COSMIC cell line database and retrieves basic sample metadata.

find_cosmic_cell_line.py

from BeautifulSoup import BeautifulSoup
import urllib2
import re


def fetch_page_soup(url):
    """ Fetches page data from a URL and returns a parsed BeautifulSoup object """

    try:
        response = urllib2.urlopen(url)
        soup = BeautifulSoup(response.read())
    finally:
        if response:
            response.close()

    return soup


def find_cosmic_cell_line(cosmic_id):
    """ Returns a COSMIC cell line's annotation, given a COSMIC ID. """

    url = r'http://cancer.sanger.ac.uk/cosmic/sample/overview?id=%s'%(str(cosmic_id))
    soup = fetch_page_soup(url)

    metadata = {}

    #The sample metadata is stored in the "overview" tab
    if soup.find("div", id="overview"):
        soup = soup.find("div", id="overview").find("div", {"class":re.compile("w75")})

        #Zip the metadata up into a dictionary
        metadata = dict(zip([x.string for x in soup.findAll("dt")], [x.string for x in soup.findAll("dd")]))

        #The sample name will not properly parse this way, so we have to pluck it out separately.
        metadata["Sample name"] = soup.find(text="Sample name").findNext("dd").find("a").string

    return metadata

if __name__ == "__main__":

    cosmic_id = 905965
    results = find_cosmic_cell_line(id)
    for k,v in results.items():
        print "%s\t%s"%(k,v)