openmedialibrary/oml/meta/abebooks.py

50 lines
1.5 KiB
Python
Raw Normal View History

2014-05-17 14:26:59 +00:00
# -*- coding: utf-8 -*-
# vi:si:et:sw=4:sts=4:ts=4
from __future__ import division
2014-05-14 09:57:11 +00:00
from ox.cache import read_url
import re
import lxml.html
2014-05-17 14:26:59 +00:00
import logging
logger = logging.getLogger('meta.abebooks')
2014-05-18 23:24:04 +00:00
base = 'http://www.abebooks.com'
2014-05-14 09:57:11 +00:00
def get_ids(key, value):
ids = []
2014-05-21 00:02:21 +00:00
if key == 'isbn':
2014-05-14 09:57:11 +00:00
url = '%s/servlet/SearchResults?isbn=%s&sts=t' % (base, id)
data = read_url(url)
urls = re.compile('href="(/servlet/BookDetailsPL[^"]+)"').findall(data)
if urls:
ids.append((key, value))
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)
2014-05-18 23:24:04 +00:00
data = {}
2014-05-14 09:57:11 +00:00
url = '%s/servlet/SearchResults?isbn=%s&sts=t' % (base, id)
2014-05-18 23:24:04 +00:00
html = read_url(url)
urls = re.compile('href="(/servlet/BookDetailsPL[^"]+)"').findall(html)
keys = {
'pubdate': 'date'
}
2014-05-14 09:57:11 +00:00
if urls:
details = '%s%s' % (base, urls[0])
2014-05-18 23:24:04 +00:00
html = read_url(details)
doc = lxml.html.document_fromstring(html)
2014-05-14 09:57:11 +00:00
for e in doc.xpath("//*[contains(@id, 'biblio')]"):
key = e.attrib['id'].replace('biblio-', '')
2014-05-26 08:23:10 +00:00
value = e.text_content().strip()
k = keys.get(key, key)
if k == 'date' and value == 'Publication Date:':
value = ''
elif k == 'publisher' and value == 'Publisher:':
value = ''
2014-05-18 23:24:04 +00:00
if value and key not in ('bookcondition', 'binding', 'edition-amz'):
2014-05-26 08:23:10 +00:00
data[k] = value
2014-05-18 23:24:04 +00:00
return data