use python logging

oml/meta/__init__.py

@@ -2,6 +2,9 @@
 # vi:si:et:sw=4:sts=4:ts=4
 from __future__ import division
 
+import logging
+logger = logging.getLogger('meta')
+
 import abebooks
 import loc
 import lookupbyisbn
@@ -41,7 +44,7 @@ def lookup(key, value):
                     if not kv in ids:
                         ids.append(kv)
                         done = False
-    print 'lookup %s=%s =>' % ids[0], ids
+    logger.debug('lookup %s=%s => %s' % ids[0][0], ids[0][1], ids)
     for k, v in ids:
         for provider, id in providers:
             if id == k and provider not in provider_data:
@@ -50,7 +53,7 @@ def lookup(key, value):
         provider_data.keys(),
         key=lambda x: -len(provider_data[x])
     ):
-        print provider, len(provider_data[provider]), provider_data[provider].keys()
+        logger.debug('%s %s %s', provider, len(provider_data[provider]), provider_data[provider].keys())
         for k_, v_ in provider_data[provider].iteritems():
             if not k_ in data:
                 data[k_] = v_

oml/meta/abebooks.py

@@ -1,7 +1,14 @@
+# -*- coding: utf-8 -*-
+# vi:si:et:sw=4:sts=4:ts=4
+from __future__ import division
+
 from ox.cache import read_url
 import re
 import lxml.html
 
+import logging
+logger = logging.getLogger('meta.abebooks')
+
 def get_ids(key, value):
     ids = []
     if key in ('isbn10', 'isbn13'):
@@ -12,12 +19,11 @@ def get_ids(key, value):
         if urls:
             ids.append((key, value))
     if ids:
-        print 'abebooks.get_ids', key, value
-        print ids
+        logger.debug('get_ids %s %s => %s', key, value, ids)
     return ids
 
 def lookup(id):
-    print 'abebooks.lookup', id
+    logger.debug('lookup %s', id)
     return {}
 
 def get_data(id):

oml/meta/duckduckgo.py

@@ -7,9 +7,12 @@ import stdnum.isbn
 
 from .utils import find_isbns
 
+import logging
+logger = logging.getLogger('meta.duckduckgo')
+
 
 def find(title, author=None, publisher=None, date=None):
-    print 'duckduckgo.find', title, author, publisher, date
+    logger.debug('find %s %s %s %s', title, author, publisher, date)
     query = title
     if author:
         if isinstance(author, list):

oml/meta/google.py

@@ -7,9 +7,12 @@ import stdnum.isbn
 
 from .utils import find_isbns
 
+import logging
+logger = logging.getLogger('meta.google')
+
 
 def find(title, author=None, publisher=None, date=None):
-    print 'google.find', title, author, publisher, date
+    logger.debug('find %s %s %s %s', title, author, publisher, date)
     query = title
     if author:
         if isinstance(author, list):
@@ -19,7 +22,7 @@ def find(title, author=None, publisher=None, date=None):
     isbns = []
     for r in ox.web.google.find(query):
         isbns += find_isbns(' '.join(r))
-    print isbns, 'google'
+    logger.debug('isbns', isbns)
     results = []
     done = set()
     for isbn in isbns:

oml/meta/loc.py

@@ -10,6 +10,9 @@ import xml.etree.ElementTree as ET
 from utils import normalize_isbn
 from marc_countries import COUNTRIES
 
+import logging
+logger = logging.getLogger('meta.loc')
+
 def get_ids(key, value):
     ids = []
     if key in ['isbn10', 'isbn13']:
@@ -19,12 +22,11 @@ def get_ids(key, value):
         if match:
             ids.append(('lccn', match.group(1)))
     if ids:
-        print 'loc.get_ids', key, value
-        print ids
+        logger.debug('get_ids %s,%s => %s', key, value, ids)
     return ids
 
 def lookup(id):
-    print 'loc.lookup', id
+    logger.debug('lookup %s', id)
     ns = '{http://www.loc.gov/mods/v3}'
     url = 'http://lccn.loc.gov/%s/mods' % id
     data = read_url(url)

oml/meta/lookupbyisbn.py

@@ -3,6 +3,9 @@ from ox import find_re, strip_tags, decode_html
 import re
 import stdnum.isbn
 
+import logging
+logger = logging.getLogger('meta.lookupbyisbn')
+
 base = 'http://www.lookupbyisbn.com'
 
 def get_ids(key, value):
@@ -20,12 +23,11 @@ def get_ids(key, value):
         if stdnum.isbn.is_valid(value):
             ids.append(('isbn10', value))
     if ids:
-        print 'lookupbyisbn.get_ids', key, value
-        print ids
+        logger.debug('get_ids %s, %s => %s', key, value, ids)
     return ids
 
 def lookup(id):
-    print 'lookupbyisbn.lookup', id
+    logger.debug('lookup %s', id)
     r = {
         'asin': id
     }

oml/meta/openlibrary.py

@@ -9,6 +9,9 @@ import json
 from marc_countries import COUNTRIES
 from utils import normalize_isbn
 
+import logging
+logger = logging.getLogger('meta.openlibrary')
+
 KEYS = {
     'authors': 'author',
     'covers': 'cover',
@@ -31,7 +34,7 @@ def find(*args, **kargs):
     args = [a.replace(':', ' ') for a in args]
     for k in ('date', 'publisher'):
         if k in kargs:
-            print 'ignoring %s on openlibrary' % k, kargs[k]
+            logger.debug('ignoring %s on openlibrary %s', k, kargs[k])
             del kargs[k]
     for k, v in kargs.iteritems():
         key = KEYS.keys()[KEYS.values().index(k)]
@@ -43,7 +46,7 @@ def find(*args, **kargs):
             args += v
     query = ' '.join(args)
     query = query.strip()
-    print 'openlibrary.find', query
+    logger.debug('find %s', query)
     r = api.search(query)
     results = []
     ids = [b for b in r.get('result', []) if b.startswith('/books')]
@@ -66,7 +69,7 @@ def get_ids(key, value):
                     if (id, v) not in ids:
                         ids.append((id, v))
     elif key in ('isbn10', 'isbn13', 'oclc', 'lccn'):
-        print 'openlibraryid.get_ids', key, value
+        logger.debug('openlibraryid.get_ids %s %s', key, value)
         r = api.things({'type': '/type/edition', key.replace('isbn', 'isbn_'): value})
         for b in r.get('result', []):
             if b.startswith('/books'):
@@ -75,8 +78,7 @@ def get_ids(key, value):
                     if kv not in ids:
                         ids.append(kv)
     if ids:
-        print 'openlibraryid.get_ids', key, value
-        print ids
+        logger.debug('get_ids %s %s => %s', key, value, ids)
     return ids
 
 def lookup(id, return_all=False):
@@ -86,7 +88,7 @@ def lookup(id, return_all=False):
     #info = json.loads(read_url(url))
     data = format(info, return_all)
     data['olid'] = id
-    print 'openlibrary.lookup', id, data.keys()
+    logger.debug('lookup %s => %s', id, data.keys())
     return data
 
 def format(info, return_all=False):
@@ -133,8 +135,8 @@ class API(object):
         url = self.base + '/' + action + '?' + urlencode(data)
         result = json.loads(read_url(url))
         if 'status' in result and result['status'] == 'error' or 'error' in result:
-            print 'FAILED', action, data
-            print 'URL', url
+            logger.info('FAILED %s %s', action, data)
+            logger.info('URL %s', url)
         return result
 
     def get(self, key):
@@ -152,7 +154,7 @@ class API(object):
             }
         data = self._request('search', {'q': query})
         if 'status' in data and data['status'] == 'error':
-            print 'FAILED', query
+            logger.info('FAILED %s', query)
         return data
 
     def things(self, query):

oml/meta/scraper.py

@@ -1,32 +0,0 @@
-import json
-from ox.cache import read_url
-import ox.web.lookupbyisbn
-
-from utils import normalize_isbn
-
-import openlibrary as ol
-
-def add_lookupbyisbn(item): 
-    isbn = item.meta.get('isbn10', item.meta.get('isbn13'))
-    if isbn:
-        more = ox.web.lookupbyisbn.get_data(isbn)
-        if more:
-            for key in more:
-                if more[key]:
-                    value = more[key]
-                    if isinstance(value, basestring):
-                        value = ox.strip_tags(ox.decode_html(value))
-                    elif isinstance(value, list):
-                        value = [ox.strip_tags(ox.decode_html(v)) for v in value]
-                    item.meta[key] = value
-
-        if 'author' in item.meta and isinstance(item.meta['author'], basestring):
-            item.meta['author'] = [item.meta['author']]
-        if 'isbn' in item.meta:
-            del item.meta['isbn']
-
-def update_ol(item):
-    info = ol.info(item.meta['olid'])
-    for key in info:
-        item.meta[key] = info[key]
-

oml/meta/worldcat.py

@@ -8,6 +8,9 @@ import re
 from utils import normalize_isbn
 import stdnum.isbn
 
+import logging
+logger = logging.getLogger('meta.worldcat')
+
 base_url = 'http://www.worldcat.org'
 
 def get_ids(key, value):
@@ -28,8 +31,8 @@ def get_ids(key, value):
             if k in info:
                 ids.append((k, info[k]))
     if ids:
-        print 'worldcat.get_ids', key, value
-        print ids
+        logger.debug('get_ids %s %s', key, value)
+        logger.debug('%s', ids)
     return ids
 
 def lookup(id):
@@ -58,8 +61,7 @@ def lookup(id):
                 data['isbn%d'%len(isbn)] = isbn
     if 'author' in data:
         data['author'] = [data['author']]
-    print 'worldcat.lookup', id
-    print data.keys()
+    logger.debug('lookup %s => %s', id, data.keys())
     return data
 
 info = lookup