Merge branch 'production2'

core/bookloader.py

@@ -223,11 +223,15 @@ def add_related(isbn):
     """
     # make sure the seed edition is there
     logger.info("adding related editions for %s", isbn)
+    
+    new_editions = []
+
     edition = add_by_isbn(isbn)
+    if edition is None:
+        return new_editions
 
     # this is the work everything will hang off
     work = edition.work
-    new_editions = []
     other_editions = {}
     for other_isbn in thingisbn(isbn):
         # 979's come back as 13

core/librarything.py

@@ -131,6 +131,9 @@ class LibraryThing(object):
             # isbn
             try:
                 book_data["isbn"] = cols[4].xpath('.//span')[0].text
+                # check for &nbsp
+                if book_data["isbn"] == u'\xA0':
+                    book_data["isbn"] = None
             except Exception, e:
                 book_data["isbn"] = None
             
@@ -143,6 +146,8 @@ class LibraryThing(object):
         # we can vary viewstyle to get different info
         
         IMPLEMENTED_STYLES = [1,5]
+        COLLECTION = 2 # set to get All Collections
+        
         if view_style not in IMPLEMENTED_STYLES:
             raise NotImplementedError()
         style_parser = getattr(self,"viewstyle_%s" % view_style)
@@ -151,8 +156,8 @@ class LibraryThing(object):
         cookies = None
         
         while next_page:
-            url = "http://www.librarything.com/catalog_bottom.php?view=%s&viewstyle=%d&offset=%d" % (self.username,
-                                        view_style, offset)
+            url = "http://www.librarything.com/catalog_bottom.php?view=%s&viewstyle=%d&collection=%d&offset=%d" % (self.username,
+                                        view_style, COLLECTION, offset)
             logger.info("url: %s", url)
             if cookies is None:
                 r = requests.get(url)
@@ -163,6 +168,7 @@ class LibraryThing(object):
                 raise LibraryThingException("Error accessing %s: %s" % (url, e))
                 logger.info("Error accessing %s: %s", url, e)
             etree = html.fromstring(r.content)
+            #logger.info("r.content %s", r.content)
             cookies = r.cookies  # retain the cookies
             
             # look for a page bar

test/booktests.py

@@ -0,0 +1,28 @@
+from regluit.core import librarything, bookloader
+import itertools
+import django
+
+def ry_lt_books():
+    """return parsing of rdhyee's LibraryThing collection"""
+    lt = librarything.LibraryThing('rdhyee')
+    books = lt.parse_user_catalog(view_style=5)
+    return books
+
+def editions_for_lt(books):
+    """return the Editions that correspond to the list of LibraryThing books"""
+    editions = [bookloader.add_by_isbn(b["isbn"]) for b in books]
+    return editions
+
+def ry_lt_not_loaded():
+    """Calculate which of the books on rdhyee's librarything list don't yield Editions"""
+    books = list(ry_lt_books())
+    editions = editions_for_lt(books)
+    not_loaded_books = [b for (b, ed) in itertools.izip(books, editions) if ed is None]
+    return not_loaded_books
+
+def ry_wish_list_equal_loadable_lt_books():
+    """returnwhether the set of works in the user's wishlist is the same as the works in a user's loadable editions from LT"""
+    editions = editions_for_lt(ry_lt_books())
+    # assume only one user -- and that we have run a LT book loading process for that user
+    ry = django.contrib.auth.models.User.objects.all()[0]
+    return set([ed.work for ed in filter(None, editions)]) == set(ry.wishlist.works.all())