python3 migration

oml/meta/abebooks.py

@@ -16,7 +16,7 @@ def get_ids(key, value):
     ids = []
     if key == 'isbn':
         url = '%s/servlet/SearchResults?isbn=%s&sts=t' % (base, id)
-        data = read_url(url)
+        data = read_url(url, unicode=True)
         urls = re.compile('href="(/servlet/BookDetailsPL[^"]+)"').findall(data)
         if urls:
             ids.append((key, value))
@@ -28,14 +28,14 @@ def lookup(id):
     logger.debug('lookup %s', id)
     data = {}
     url = '%s/servlet/SearchResults?isbn=%s&sts=t' % (base, id)
-    html = read_url(url)
+    html = read_url(url, unicode=True)
     urls = re.compile('href="(/servlet/BookDetailsPL[^"]+)"').findall(html)
     keys = {
         'pubdate': 'date'
     }
     if urls:
         details = '%s%s' % (base, urls[0])
-        html = read_url(details)
+        html = read_url(details, unicode=True)
         doc = lxml.html.document_fromstring(html)
         for e in doc.xpath("//*[contains(@id, 'biblio')]"):
             key = e.attrib['id'].replace('biblio-', '')

oml/meta/dewey.py

@@ -942,7 +942,7 @@ if __name__ == '__main__':
     for i in range(0, 1000):
         url = 'http://dewey.info/class/%s/about.en.json' % i
         print(url)
-        data = json.loads(read_url(url))
+        data = json.loads(read_url(url).decode('utf-8'))
         for d in list(data.values()):
             if 'http://www.w3.org/2004/02/skos/core#prefLabel' in d:
                 value = d['http://www.w3.org/2004/02/skos/core#prefLabel'][0]['value']

oml/meta/loc.py

@@ -19,7 +19,7 @@ def get_ids(key, value):
     ids = []
     if key == 'isbn':
         url = 'http://www.loc.gov/search/?q=%s&all=true' % value
-        html = ox.cache.read_url(url)
+        html = ox.cache.read_url(url).decode('utf-8')
         match = re.search('"http://lccn.loc.gov/(\d+)"', html)
         if match:
             ids.append(('lccn', match.group(1)))
@@ -37,7 +37,7 @@ def 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)
+    data = read_url(url).decode('utf-8')
     mods = ET.fromstring(data)
 
     info = {

oml/meta/lookupbyisbn.py

@@ -89,5 +89,5 @@ def lookup(id):
     return r
 
 def amazon_lookup(asin):
-    html = read_url('http://www.amazon.com/dp/%s' % asin)
+    html = read_url('http://www.amazon.com/dp/%s' % asin).decode('utf-8')
     return list(set(find_isbns(find_re(html, 'Formats</h3>.*?</table'))))

oml/meta/marc_countries.py

@@ -392,7 +392,7 @@ if __name__ == '__main__':
     from ox.cache import read_url
 
     url = "http://www.loc.gov/marc/countries/countries_code.html"
-    data = read_url(url)
+    data = read_url(url).decode('utf-8')
     countries = dict([
         [ox.strip_tags(c) for c in r]
         for r in re.compile('<tr>.*?class="code">(.*?)</td>.*?<td>(.*?)</td>', re.DOTALL).findall(data)

oml/meta/openlibrary.py

@@ -78,7 +78,7 @@ def lookup(id, return_all=False):
     logger.debug('lookup %s', id)
     info = api.get('/books/' + id).get('result', {})
     #url = 'https://openlibrary.org/books/%s.json' % id
-    #info = json.loads(read_url(url))
+    #info = json.loads(read_url(url).decode('utf-8'))
     data = format(info, return_all)
     if 'olid' not in data:
         data['olid'] = []
@@ -164,9 +164,9 @@ class API(object):
                 data[key] = json.dumps(data[key])
         url = self.base + '/' + action + '?' + urlencode(data)
         if timeout is None:
-            result = json.loads(read_url(url))
+            result = json.loads(read_url(url).decode('utf-8'))
         else:
-            result = json.loads(read_url(url, timeout=timeout))
+            result = json.loads(read_url(url, timeout=timeout).decode('utf-8'))
         if 'status' in result and result['status'] == 'error' or 'error' in result:
             logger.info('FAILED %s %s', action, data)
             logger.info('URL %s', url)

oml/meta/worldcat.py

@@ -21,7 +21,7 @@ def get_ids(key, value):
     ids = []
     if key == 'isbn':
         url = '%s/search?qt=worldcat_org_bks&q=%s' % (base_url, value)
-        html = read_url(url)
+        html = read_url(url).decode('utf-8')
         matches = re.compile('/title.*?oclc/(\d+).*?"').findall(html)
         if matches:
             info = lookup(matches[0])