def get_total_entries_by_yr(year):
return fc.search(lookfor="",
search_type=fst.Subject,
fields=["year"],
filters=[("main_date_str:" + str(year))],
page=1,
limit=100)['resultCount']
def get_response(pg, search_query, year):
return fc.search(lookfor=search_query,
search_type=fst.Subject,
fields=["title", "buildings", "subjects"],
filters=[("main_date_str:" + str(year))],
facets=["author"],
page=pg,
limit=100)
def get_tree(year):
finna = FinnaClient()
sk = SkosmosClient()
records = finna_search(year, finna)
chains = [get_keyword_chain(x.subject, sk) for x in records]
chains = [x for x in chains if x is not None]
trees = [create_tree(x) for x in chains]
return join_trees(trees)
def finna_search(searchwords, filters = [], limit = 10):
res = []
resultcount = 0
finna = FinnaClient()
for word in searchwords:
result = finna.search(word,
#search_type=FinnaSearchType.Author,
fields=['title','nonPresenterAuthors','id','formats','subjects','year','languages','primaryAuthors'],
filters=filters,
#sort=FinnaSortMethod.main_date_str_desc,
limit=limit)
res.extend(result["records"])
resultcount += result['resultCount']
results = []
for item in res:
if item not in results:
item['url'] = "https://www.finna.fi/Record/"+item['id']
if 'formats' in item and len(item['formats']):
item['formats'] = item['formats'][0]
else:
item['formats'] = {'translated': ''}
results.append(item)
# from pprint import pprint
# pprint(results[0])
# {'formats': [{'translated': 'Kirja', 'value': '0/Book/'},
# {'translated': 'Kirja', 'value': '1/Book/Book/'}],
# 'id': 'alli.313062',
# 'languages': ['eng'],
# 'nonPresenterAuthors': [{'name': 'Koolhaas, Rem'}],
# 'primaryAuthors': [],
# 'subjects': [],
# 'title': 'Content',
# 'url': 'https://www.finna.fi/Record/alli.313062',
# 'year': '2004'}
return results
from finna_client import FinnaClient
finna = FinnaClient()
results = finna.search("bicycle", limit=5)
for rec in results['records']:
print(rec['title'])
from annif_client import AnnifClient
annif = AnnifClient()
results = annif.analyze(project_id='yso-en',
text="The quick brown fox",
limit=5)
for result in results:
print(result)
def __init__(self):
self.client = FinnaClient()
#!/usr/bin/env python
import json
from http.server import BaseHTTPRequestHandler, HTTPServer
from finna_client import FinnaClient
from places import Places
from search import paged_search, vectorized
finna = FinnaClient()
places = Places('yso-paikat-skos.rdf')
cache = {}
class RequestHandler(BaseHTTPRequestHandler):
def do_GET(self):
if 'api' in self.path:
subject = self.path.strip().split('/')[2]
print(subject)
if not subject in cache:
results = paged_search(finna, subject, places)
vector = vectorized(results, places)
cache[subject] = vector
vector = cache[subject]
#geojson = {"type": "Feature", "geometry": { "type": "Polygon", "coordinates": vector}}
self.send_response(200)
self.send_header('Content-type', 'text/json')
from finna_client import FinnaClient, FinnaSearchType, FinnaSortMethod
import urllib
from PIL import Image
import requests
from io import BytesIO
import os
LIMIT = 100
SUBJECT = 'soutuveneet'
row_path = 'data/rowboats'
os.mkdirs(row_paths)
os.mkdirs('checkpoints')
finna = FinnaClient()
result = finna.search(SUBJECT,
search_type=FinnaSearchType.Subject,
limit=0,
filters=['format:0/Image/', 'online_boolean:1'])
pages = result['resultCount'] // LIMIT
urls = []
for page in range(pages):
result = finna.search(SUBJECT,
search_type=FinnaSearchType.Subject,
filters=['format:0/Image/', 'online_boolean:1'],
fields=['images'],
sort=FinnaSortMethod.main_date_str_asc,
limit=LIMIT,