1 

     2 import httplib2

     3 import anyjson

     4 from lxml import etree

     5 import sys

     6 import pprint

     7 

     8 def get_stats(url):

     9     

    10     h = httplib2.Http()

    11     resp, content = h.request(url)    

    12     #project = anyjson.deserialize(content)

    13     root = etree.fromstring(content)

    14 

    15     #get all annotations

    16     res_xpath = root.xpath("//ensemble[starts-with(@id,'tweet_')]//element")

    17     

    18     total_annot = len(res_xpath)

    19     total_with_polemic = 0

    20     total_by_type = {}

    21     

    22     

    23     for annot in res_xpath:

    24         polemic_list = annot.xpath("meta/polemics/polemic")

    25         if len(polemic_list)> 0:

    26             total_with_polemic += 1

    27             for polemic_item in polemic_list:

    28                 pol_type = polemic_item.text

    29                 total_by_type[pol_type] = total_by_type.get(pol_type,0) + 1

    30             

    31             

    32     return {"total_annotations": total_annot, "total_with_polemics": total_with_polemic, "polemic_by_type": total_by_type}

    33 

    34 if __name__ == "__main__":

    35     

    36     pp = pprint.PrettyPrinter(indent=4, width=1)

    37     

    38     pp.pprint(get_stats(sys.argv[1]))