I've been trying to use html5lib with lxml on python 2.7 in google app engine. But when I run the following code, it gives me an error saying "NameError: global name 'etree' is not defined". Is it not possible to use lxml.etree on google app engine? or am I missing something?
app.yaml
application: testsite version: 1 runtime: python27 api_version: 1 threadsafe: false handlers: - url: /.* script: index.py libraries: - name: lxml version: "2.3" # I thought this would allow me to use lxml.etree
index.py
from testhandler import TestHandler application = webapp.WSGIApplication([('/', TestHandler)], debug=True)
testhandler.py
import urllib2 import html5lib from html5lib import treebuilders try: from lxml import etree print("running with lxml.etree") except ImportError: try: # Python 2.5 import xml.etree.cElementTree as etree print("running with cElementTree on Python 2.5+") except ImportError: try: # Python 2.5 import xml.etree.ElementTree as etree print("running with ElementTree on Python 2.5+") except ImportError: try: # normal cElementTree install import cElementTree as etree print("running with cElementTree") except ImportError: try: # normal ElementTree install import elementtree.ElementTree as etree print("running with ElementTree") except ImportError: print("Failed to import ElementTree from any known place") from google.appengine.ext import webapp class TestHandler(webapp.RequestHandler): def get(self): f = urllib2.urlopen("http://www.yahoo.com/").read() doc = html5lib.parse(f, treebuilder='lxml') elems = doc.xpath("//*[local-name() = 'a']") self.response.out.write(len(elems))
error
running with cElementTree on Python 2.5+ Status: 500 Internal Server Error Content-Type: text/html; charset=utf-8 Cache-Control: no-cache Expires: Fri, 01 Jan 1990 00:00:00 GMT Content-Length: 769 <pre>Traceback (most recent call last): File "/usr/local/bin/google_appengine/google/appengine/ext/webapp/_webapp25.py", line 701, in __call__ handler.get(*groups) File "/home/test/testhandler.py", line 38, in get parser = html5lib.HTMLParser(tree= treebuilders.getTreeBuilder('lxml')) File "/home/test/html5lib/html5parser.py", line 68, in __init__ self.tree = tree(namespaceHTMLElements) File "/home/test/html5lib/treebuilders/etree_lxml.py", line 176, in __init__ builder = etree_builders.getETreeModule(etree, fullTree=fullTree) NameError: global name 'etree' is not defined </pre>
ADD
Nah, I tried several ways to create a doc object, but no luck. One of the ways, I tried to import from lxml.html import document_fromstring
and that gives me this error.
Traceback (most recent call last): File "/usr/local/bin/google_appengine/google/appengine/tools/dev_appserver.py", line 4143, in _HandleRequest self._Dispatch(dispatcher, self.rfile, outfile, env_dict) File "/usr/local/bin/google_appengine/google/appengine/tools/dev_appserver.py", line 4049, in _Dispatch base_env_dict=env_dict) File "/usr/local/bin/google_appengine/google/appengine/tools/dev_appserver.py", line 616, in Dispatch base_env_dict=base_env_dict) File "/usr/local/bin/google_appengine/google/appengine/tools/dev_appserver.py", line 3120, in Dispatch self._module_dict) File "/usr/local/bin/google_appengine/google/appengine/tools/dev_appserver.py", line 3024, in ExecuteCGI reset_modules = exec_script(handler_path, cgi_path, hook) File "/usr/local/bin/google_appengine/google/appengine/tools/dev_appserver.py", line 2887, in ExecuteOrImportScript exec module_code in script_module.__dict__ File "/home/yoo/eclipse_workspace/website_checker/src/index.py", line 5, in <module> from handlers.updatecheck import UpdateCheckHandler File "/usr/local/bin/google_appengine/google/appengine/tools/dev_appserver.py", line 1538, in Decorate return func(self, *args, **kwargs) File "/usr/local/bin/google_appengine/google/appengine/tools/dev_appserver.py", line 2503, in load_module return self.FindAndLoadModule(submodule, fullname, search_path) File "/usr/local/bin/google_appengine/google/appengine/tools/dev_appserver.py", line 1538, in Decorate return func(self, *args, **kwargs) File "/usr/local/bin/google_appengine/google/appengine/tools/dev_appserver.py", line 2375, in FindAndLoadModule description) File "/usr/local/bin/google_appengine/google/appengine/tools/dev_appserver.py", line 1538, in Decorate return func(self, *args, **kwargs) File "/usr/local/bin/google_appengine/google/appengine/tools/dev_appserver.py", line 2318, in LoadModuleRestricted description) File "/home/test/updatecheck.py", line 4, in <module> from lxml.html import document_fromstring File "/usr/local/bin/google_appengine/google/appengine/tools/dev_appserver.py", line 1538, in Decorate return func(self, *args, **kwargs) File "/usr/local/bin/google_appengine/google/appengine/tools/dev_appserver.py", line 2503, in load_module return self.FindAndLoadModule(submodule, fullname, search_path) File "/usr/local/bin/google_appengine/google/appengine/tools/dev_appserver.py", line 1538, in Decorate return func(self, *args, **kwargs) File "/usr/local/bin/google_appengine/google/appengine/tools/dev_appserver.py", line 2375, in FindAndLoadModule description) File "/usr/local/bin/google_appengine/google/appengine/tools/dev_appserver.py", line 1538, in Decorate return func(self, *args, **kwargs) File "/usr/local/bin/google_appengine/google/appengine/tools/dev_appserver.py", line 2318, in LoadModuleRestricted description) File "/usr/lib/python2.7/dist-packages/lxml/html/__init__.py", line 12, in <module> from lxml import etree ImportError: cannot import name etree
According to the error, it seems app engine doesn't allow me to load etree module for some reason. I wanted to use xpath with lxml, but I can't spend much time to figure out what is going on here and don't have enough knowledge of python either. So I would give a try to find a way with 'simpletree' version.
f = urllib2.urlopen("http://www.yahoo.com/").read() p = html5lib.HTMLParser() doc = p.parse(f) # do something with doc.childNodes self.response.out.write(len(doc.childNodes))
Not really a good way, but at least it worked when I tested on live google app engine.