Example of how to iterate over solr results as if it's just a list of documents

pager.py

#!/usr/bin/python

from random import randint

class QueryResult(object):
    """Mock representation of a set of matching results to a query"""
    def __init__(self,query,max_results):
        self.query = query
        self.count = randint(1,max_results)

    def get_results(self,start,page_size=10):
        current = start
        docs = []
        # this dict looks sort of like a page of results from Solr
        result = { "query" : self.query, "start": start, "numFound": self.count, "docs": docs }
        while current < self.count and len(docs) < page_size:
            docs.append({"id": "doc-{}".format(current+1),
                         "title" : "Title #{}".format(current+1)})
            current += 1
        return result 
        
class MockServer(object):
    """Mock Solr server; remembers doc counts for queries and can return results in a given batch size"""
    def __init__(self,doc_count=5000):
        self.doc_count = doc_count
        self.active_queries = {}

    def query(self,query,start=0,page_size=10):
        if query in self.active_queries:
            result = self.active_queries[query]
        else:
            result = QueryResult(query,self.doc_count)
            self.active_queries[query] = result
        return result.get_results(start,page_size)

# everything above this line is a simulation of a thing that delivers
# results in chunks like a Solr server
            

def iterate_results(query,page_size):
    """Wrapper over mocks above that can be iterated over to retrieve each matching document in turn"""

    # with real Solr library, the next line would be where you establish
    # a connection to the server
    server = MockServer()
    # initial query; gives us number of hits and a batch of results
    results = server.query(query)
    last_index = 0
    num_found = results['numFound']
    print("Initial query says {} hits for '{}'".format(num_found,query))
    while last_index < num_found:
        for doc in results['docs']:
            yield doc
        last_index = results['start'] + len(results['docs'])
        results = server.query(query,last_index)

   
# and now ... we iterate! 

if __name__ == '__main__':
    import sys
    # invocation: ./pager.py [query] [page size]
    query = len(sys.argv) > 1 and sys.argv[1] or 'some_query'
    page_size = 10
    if len(sys.argv) > 2:
        try:
            page_size = int(sys.argv[2])
        except:
            pass

    index = 0
    result_modulus = 12
    
    print("printing every {}th result".format(result_modulus))
    for doc in iterate_results(query,page_size):
        if index % result_modulus == 0:
            print("\t{}".format(doc['title']))
        index += 1
    print("Last doc: {}".format(doc['title']))