def lucid_training_docs(query, num_records=1000):
query_list = query.split()
if len(query_list) == 1: #single term
term_query = 'content:'+query
else:
term_query = ' AND '.join(['content:'+q for q in query_list])
#collection = 'crawl_from_long_fashion_blogs_list'
collection = 'fashion_crawl_try_20131015'
field_string = ','.join( ('content', 'score') )
config = Config()
config.http_debug = True
solr = Solr(config)
json_response = solr.query_solr(
collection=collection,
query=term_query,
field_string=field_string,
start=0,
rows=num_records)
response = simplejson.loads(json_response)
response['response']['numFound']
docs = response['response']['docs']
pages = []
for i in range(len(docs)):
page = docs[i]['content'][0]
pages.append(page.encode('utf-8') )
return pages
collection = 'neiman_marcus_raw_catalog'
field_string = ','.join(
(
'cmos_item_code',
'long_desc_text_only',
'detail_bullets'
)
)
delim = '\t'
multi_value_delim = '.'
escape_newlines = False
#################################
config = Config()
config.http_debug = True
solr = Solr(config)
worked = solr.query_to_file(
out_file_path=out_file_path,
query_string=query_string,
max_records=max_records,
collection=collection,
field_string=field_string,
delim=delim,
multi_value_delim=multi_value_delim,
escape_newlines=escape_newlines,
)
if worked:
print out_file_path + ' Done!'
else:
