Python eTree Parser 没有附加元素答案

【问题标题】：Python eTree Parser isn't appending an elementPython eTree Parser 没有附加元素
【发布时间】：2013-05-09 17:30:40
【问题描述】：

查看我的日志，看看我从 Postgres 返回的行是如何从字符串变成元素的（我打印字符串，打印元素，打印 isElement 布尔值！）然而当我尝试附加它时，错误是它不是一个元素。呵呵，呵呵。

import sys
from HTMLParser import HTMLParser
from xml.etree import cElementTree as etree
import xml.etree.ElementTree as ET
from xml.etree.ElementTree import Element, SubElement, tostring
import psycopg2
import psycopg2.extras

def main():
    # Connect to an existing database
    conn = psycopg2.connect(dbname="**", user="**", password="**", host="/tmp/", port="**")

    # Open a cursor to perform database operations
    cur = conn.cursor(cursor_factory = psycopg2.extras.RealDictCursor)

    cur.execute("SELECT * FROM landingpagedata;")
    rows = cur.fetchall()

    class LinksParser(HTMLParser):
      def __init__(self):
          HTMLParser.__init__(self)
          self.tb = etree.TreeBuilder()

      def handle_starttag(self, tag, attributes):
          self.tb.start(tag, dict(attributes))

      def handle_endtag(self, tag):
          self.tb.end(tag)

      def handle_data(self, data):
          self.tb.data(data)

      def close(self):
          HTMLParser.close(self)
          return self.tb.close()

    template = 'template.html'



    # parser.feed(open('landingIndex.html').read()) #for testing
    # root = parser.close()

    for row in rows:
        parser = LinksParser()

        parser.feed(open(template).read())
        root = parser.close()




        #title
        title = root.find(".//title")
        title.text = row['title']

        #headline
        h1_id_headline = root.find(".//h1")
        h1_id_headline.text = row['h1_id_headline']
        # print row['h1_id_headline']

        #intro
        p_class_intro = root.find(".//p[@class='intro']")
        p_class_intro.text = row['p_class_intro']
        # print row['p_class_intro']

这就是问题所在！

        #recommended
        p_class_recommendedbackground = root.find(".//div[@class='recommended_background_div']")
        print p_class_recommendedbackground
        p_class_recommendedbackground.clear()
        newElement = ET.fromstring(row['p_class_recommendedbackground'])
        print row['p_class_recommendedbackground']
        print ET.iselement(newElement)
        p_class_recommendedbackground.append(newElement)

        html = tostring(root)
        f = open(row['page_name'], 'w').close()
        f = open(row['page_name'], 'w')
        f.write(html)
        f.close()
        # f = ''
        # html = ''
        parser.reset()
        root = ''

    # Close communication with the database
    cur.close()
    conn.close()

if __name__ == "__main__":
  main()

我的日志是这样的：

{background: url(/images/courses/azRealEstate.png) center no-repeat;}
<Element 'div' at 0x10a999720>
<p class="recommended_background">Materials are are aimed to all aspiring real estate sales associates who wish to obtain the Arizona Real Estate Salesperson license, which is provided by the <a href="http://www.re.state.az.us/" style="text-decoration: underline;">Arizona Department of Real Estate</a>.</p>
True
Traceback (most recent call last):
  File "/Users/Morgan13/Programming/LandingPageBuilder/landingPages/landingBuilderTest.py", line 108, in <module> main()
  File "/Users/Morgan13/Programming/LandingPageBuilder/landingPages/landingBuilderTest.py", line 84, in main
    p_class_recommendedbackground.append(newElement)
TypeError: must be Element, not Element
[Finished in 0.1s with exit code 1]

【问题讨论】：

标签： python html-parsing psycopg2 xml.etree

【解决方案1】：

我可以通过这种方式重现错误消息：

from xml.etree import cElementTree as etree
import xml.etree.ElementTree as ET

croot = etree.Element('root')
child = ET.Element('child')
croot.append(child)
# TypeError: must be Element, not Element

问题的根本原因是我们将ElementTree 的cElementTree 实现与ElementTree 的xml.etree.ElementTree 实现混合在一起。永远不要让双胞胎相遇。

所以解决方法就是选择一个，比如etree，然后替换所有出现的另一个（例如，将ET 替换为etree）。

【讨论】：