Я пытался использовать html5lib с lxml на python 2.7 в google app engine. Но когда я запускаю следующий код, он выдает мне сообщение «NameError: глобальное имя« etree »не определено». Разве нельзя использовать lxml.etree на движке приложений Google? или я что-то упустил?
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))
ошибка
<code>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
ADD
Нет, я пробовал несколько способов создать объект документа, но не повезло. Один из способов, я попытался импортировать from lxml.html import document_fromstring
, и это дает мне эту ошибку.
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
В соответствии с ошибкой, кажется, что движок приложения по какой-то причине не позволяет мне загрузить модуль etree. Я хотел использовать xpath с lxml, но я не могу тратить много времени на то, чтобы понять, что здесь происходит, и у меня тоже недостаточно знаний о python. Так что я бы попробовал найти способ с «простой версией».
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))
Не совсем хороший способ, но, по крайней мере, он работал, когда я тестировал на live google app engine.