use the uncanonicalized url as part of the sha1 input to generate the page id, since canonicalization was stripping off the #fragment, and we might want to crawl the same url with different fragments (and there's no option to GoogleURLCanonicalizer to not strip the fragment)

brozzler/site.py

@@ -105,8 +105,7 @@ class Page(brozzler.BaseDictable):
         if id is not None:
             self.id = id
         else:
-            digest_this = "site_id:{},canon_url:{}".format(
-                    self.site_id, self.canon_url())
+            digest_this = "site_id:{},url:{}".format(self.site_id, self.url)
             self.id = hashlib.sha1(digest_this.encode("utf-8")).hexdigest()
 
     def __repr__(self):

setup.py

@@ -2,7 +2,7 @@ import setuptools
 import glob
 
 setuptools.setup(name='brozzler',
-        version='1.1.dev4',
+        version='1.1.dev5',
         description='Distributed web crawling with browsers',
         url='https://github.com/nlevitt/brozzler',
         author='Noah Levitt',