openmedialibrary/oml/meta/lookupbyisbn.py

95 lines
3.0 KiB
Python
Raw Normal View History

2014-08-12 08:16:57 +00:00
# -*- coding: utf-8 -*-
# vi:si:et:sw=4:sts=4:ts=4
2014-09-02 22:32:44 +00:00
2014-08-12 08:16:57 +00:00
import re
2014-05-14 09:57:11 +00:00
from ox.cache import read_url
2014-05-14 18:46:31 +00:00
from ox import find_re, strip_tags, decode_html
import stdnum.isbn
2014-05-14 09:57:11 +00:00
2014-09-02 22:32:44 +00:00
from .utils import find_isbns
2014-05-21 00:02:21 +00:00
2014-05-17 14:26:59 +00:00
import logging
2015-11-29 14:56:38 +00:00
logger = logging.getLogger(__name__)
2014-05-17 14:26:59 +00:00
2014-08-12 08:16:57 +00:00
2014-05-14 09:57:11 +00:00
base = 'http://www.lookupbyisbn.com'
def get_ids(key, value):
ids = []
2014-05-21 00:02:21 +00:00
def add_other_isbn(v):
if len(v) == 10:
ids.append(('isbn', stdnum.isbn.to_isbn13(v)))
if len(v) == 13 and v.startswith('978'):
ids.append(('isbn', stdnum.isbn.to_isbn10(v)))
if key in ('isbn', 'asin'):
2014-05-14 09:57:11 +00:00
url = '%s/Search/Book/%s/1' % (base, value)
data = read_url(url).decode('utf-8')
m = re.compile('href="(/Lookup/Book/[^"]+?)"').findall(data)
if m:
asin = m[0].split('/')[-3]
2015-11-03 22:36:19 +00:00
if stdnum.isbn.to_isbn10(asin) or not stdnum.isbn.is_valid(asin):
2014-05-21 00:02:21 +00:00
ids.append(('asin', asin))
if key == 'isbn':
add_other_isbn(value)
2014-05-14 18:46:31 +00:00
if key == 'asin':
if stdnum.isbn.is_valid(value):
2014-05-21 00:02:21 +00:00
ids.append(('isbn', value))
add_other_isbn(value)
else:
for isbn in amazon_lookup(value):
if stdnum.isbn.is_valid(isbn):
ids.append(('isbn', isbn))
add_other_isbn(isbn)
2014-05-14 09:57:11 +00:00
if ids:
2014-05-17 14:26:59 +00:00
logger.debug('get_ids %s, %s => %s', key, value, ids)
2014-05-14 09:57:11 +00:00
return ids
def lookup(id):
2014-05-17 14:26:59 +00:00
logger.debug('lookup %s', id)
2014-05-14 09:57:11 +00:00
r = {
2014-05-21 00:02:21 +00:00
'asin': [id]
2014-05-14 09:57:11 +00:00
}
url = '%s/Lookup/Book/%s/%s/1' % (base, id, id)
data = read_url(url).decode('utf-8')
r["title"] = find_re(data, "<h2>(.*?)</h2>")
2014-05-26 08:23:10 +00:00
if r["title"] == 'Error!':
return {}
2014-05-14 09:57:11 +00:00
keys = {
'author': 'Author(s)',
'publisher': 'Publisher',
'date': 'Publication date',
'edition': 'Edition',
'binding': 'Binding',
'volume': 'Volume(s)',
'pages': 'Pages',
}
for key in keys:
r[key] = find_re(data, '<span class="title">%s:</span>(.*?)</li>'% re.escape(keys[key]))
2014-05-18 23:24:04 +00:00
if r[key] == '--' or not r[key]:
del r[key]
if key == 'pages' and key in r:
2014-05-14 09:57:11 +00:00
r[key] = int(r[key])
desc = find_re(data, '<h2>Description:<\/h2>(.*?)<div ')
desc = desc.replace('<br /><br />', ' ').replace('<br /> ', ' ').replace('<br />', ' ')
2014-05-16 08:06:11 +00:00
r['description'] = decode_html(strip_tags(desc))
2014-05-14 09:57:11 +00:00
r['cover'] = find_re(data, '<img src="(.*?)" alt="Book cover').replace('._SL160_', '')
2014-05-14 18:46:31 +00:00
for key in r:
2014-09-02 22:32:44 +00:00
if isinstance(r[key], str):
2014-05-14 18:46:31 +00:00
r[key] = decode_html(strip_tags(r[key])).strip()
2014-09-02 22:32:44 +00:00
if 'author' in r and isinstance(r['author'], str) and r['author']:
2014-05-14 09:57:11 +00:00
r['author'] = [r['author']]
2014-05-16 08:06:11 +00:00
else:
r['author'] = []
2014-09-02 22:32:44 +00:00
if r['description'].lower() == 'Description of this item is not available at this time.'.lower():
2014-05-16 08:06:11 +00:00
r['description'] = ''
2014-05-14 09:57:11 +00:00
return r
2014-05-21 00:02:21 +00:00
def amazon_lookup(asin):
2015-11-03 22:36:19 +00:00
url = 'http://www.amazon.com/dp/%s' % asin
html = read_url(url, timeout=-1).decode('utf-8', 'ignore')
2014-05-21 00:02:21 +00:00
return list(set(find_isbns(find_re(html, 'Formats</h3>.*?</table'))))