139 lines
4.3 KiB
Python
139 lines
4.3 KiB
Python
# -*- coding: utf-8 -*-
|
|
# vi:si:et:sw=4:sts=4:ts=4
|
|
|
|
from time import time, sleep
|
|
|
|
from ox.cache import get_json, store
|
|
import ox.web.google
|
|
import stdnum.isbn
|
|
|
|
from .utils import find_isbns, get_language, decode_html_data, to_isbn13
|
|
|
|
import logging
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def find(query):
|
|
logger.debug('find %s', query)
|
|
query += ' isbn'
|
|
isbns = []
|
|
for r in ox.web.google.find(query):
|
|
isbns += find_isbns(' '.join(r))
|
|
logger.debug('isbns', isbns)
|
|
results = []
|
|
done = set()
|
|
for isbn in isbns:
|
|
if isbn not in done:
|
|
r = {
|
|
'isbn': isbn,
|
|
'primaryid': ['isbn', isbn]
|
|
}
|
|
results.append(r)
|
|
done.add(isbn)
|
|
if len(isbn) == 10:
|
|
done.add(stdnum.isbn.to_isbn13(isbn))
|
|
if len(isbn) == 13 and isbn.startswith('978'):
|
|
done.add(stdnum.isbn.to_isbn10(isbn))
|
|
return results
|
|
|
|
def info(key, value):
|
|
if key not in ('isbn', 'lccn', 'oclc'):
|
|
raise IOError('unknwon key %s' % key)
|
|
url = 'https://www.googleapis.com/books/v1/volumes?q=%s:%s' % (key, value)
|
|
if api_limit.error:
|
|
raise IOError(url)
|
|
while not api_limit.consume(1):
|
|
logger.debug('hitting google api to fast, waiting 1 second')
|
|
sleep(1)
|
|
r = get_json(url, timeout=-1)
|
|
if 'error' in r:
|
|
logger.debug('got google api error, dont call for 10 minutes')
|
|
store.delete(url)
|
|
api_limit.error = True
|
|
raise IOError(url, r)
|
|
if not 'items' in r:
|
|
print('unknown %s: %s [%s]' % (key, value, r))
|
|
return {}
|
|
_data = r['items'][0]['volumeInfo']
|
|
_id = r['items'][0]['id']
|
|
data = {}
|
|
for key in [
|
|
'authors',
|
|
'categories',
|
|
'description',
|
|
'pageCount',
|
|
'publishedDate',
|
|
'publisher',
|
|
'title',
|
|
]:
|
|
if key in _data:
|
|
data[{
|
|
'authors': 'author',
|
|
'pageCount': 'pages',
|
|
'publishedDate': 'date',
|
|
}.get(key,key)] = _data[key]
|
|
|
|
if 'subtitle' in _data and _data['subtitle'].strip():
|
|
data['title'] = '{title}: {subtitle}'.format(**_data)
|
|
if r['items'][0]['accessInfo']['viewability'] != 'NO_PAGES':
|
|
#data['cover'] = 'https://books.google.com/books?id=%s&pg=PP1&img=1&zoom=0&hl=en' % _id
|
|
data['cover'] = 'https://books.google.com/books/content/images/frontcover/%s?fife=w600-rw' % _id
|
|
|
|
elif 'imageLinks' in _data:
|
|
for size in ('extraLarge', 'large', 'medium', 'small', 'thumbnail', 'smallThumbnail'):
|
|
if size in _data['imageLinks']:
|
|
data['cover'] = _data['imageLinks'][size]
|
|
break
|
|
if 'industryIdentifiers' in _data:
|
|
for k in _data['industryIdentifiers']:
|
|
if k['type'].startswith('ISBN'):
|
|
if not 'isbn' in data:
|
|
data['isbn'] = []
|
|
data['isbn'].append(k['identifier'])
|
|
else:
|
|
print('unknown identifier', k)
|
|
if 'isbn' in data:
|
|
data['isbn'] = [to_isbn13(i) for i in data['isbn']][0]
|
|
|
|
if 'publisher' in data and isinstance(data['publisher'], str):
|
|
data['publisher'] = [data['publisher']]
|
|
if 'language' in _data:
|
|
data['language'] = [get_language(_data['language'])]
|
|
data = decode_html_data(data)
|
|
return data
|
|
|
|
class Limit(object):
|
|
_error = False
|
|
|
|
def __init__(self, fill_rate, capacity):
|
|
self.timestamp = time()
|
|
self.fill_rate = fill_rate
|
|
self.capacity = capacity
|
|
self._tokens = capacity
|
|
|
|
def consume(self, tokens):
|
|
if tokens <= self.tokens:
|
|
self._tokens -= tokens
|
|
else:
|
|
return False
|
|
return True
|
|
|
|
def get_tokens(self):
|
|
now = time()
|
|
if self._tokens < self.capacity:
|
|
delta = self.fill_rate * (now - self.timestamp)
|
|
self._tokens = min(self.capacity, self._tokens + delta)
|
|
self.timestamp = now
|
|
return self._tokens
|
|
tokens = property(get_tokens)
|
|
|
|
def get_error(self):
|
|
if self._error and self._error < (time() - 10*60):
|
|
self._error = False
|
|
return self._error != False
|
|
|
|
def set_error(self, value):
|
|
self._error = time()
|
|
error = property(get_error, set_error)
|
|
|
|
api_limit = Limit(fill_rate=0.5, capacity=25)
|