Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- #!/usr/bin/env python
- # Your task here is to extract data from xml on authors of an article
- # and add it to a list, one item for an author.
- # See the provided data structure for the expected format.
- # The tags for first name, surname and email should map directly
- # to the dictionary keys, but you have to extract the attributes from the "insr" tag
- # and add them to the list for the dictionary key "insr"
- import xml.etree.ElementTree as ET
- article_file = "exampleResearchArticle.xml"
- def get_root(fname):
- tree = ET.parse(fname)
- return tree.getroot()
- def get_authors(root):
- authors = []
- for author in root.findall('./fm/bibl/aug/au'):
- data = {
- "fnm": None,
- "snm": None,
- "email": None,
- "insr": []
- }
- # YOUR CODE HERE
- data['fnm']= author.find('fnm').text
- data['snm']= author.find('snm').text
- data['email']= author.find('email').text
- data['insr']=author.find('insr').attrib('iid')
- authors.append(data)
- return authors
- def test():
- solution = [{'insr': ['I1'], 'fnm': 'Omer', 'snm': 'Mei-Dan', 'email': 'omer@extremegate.com'},
- {'insr': ['I2'], 'fnm': 'Mike', 'snm': 'Carmont', 'email': 'mcarmont@hotmail.com'},
- {'insr': ['I3', 'I4'], 'fnm': 'Lior', 'snm': 'Laver', 'email': 'laver17@gmail.com'},
- {'insr': ['I3'], 'fnm': 'Meir', 'snm': 'Nyska', 'email': 'nyska@internet-zahav.net'},
- {'insr': ['I8'], 'fnm': 'Hagay', 'snm': 'Kammar', 'email': 'kammarh@gmail.com'},
- {'insr': ['I3', 'I5'], 'fnm': 'Gideon', 'snm': 'Mann', 'email': 'gideon.mann.md@gmail.com'},
- {'insr': ['I6'], 'fnm': 'Barnaby', 'snm': 'Clarck', 'email': 'barns.nz@gmail.com'},
- {'insr': ['I7'], 'fnm': 'Eugene', 'snm': 'Kots', 'email': 'eukots@gmail.com'}]
- root = get_root(article_file)
- data = get_authors(root)
- assert data[0] == solution[0]
- assert data[1]["insr"] == solution[1]["insr"]
- test()
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement