Python eTree Parser가 요소를 추가하지 않음

Question

내 로그를보고 Postgres에서 돌아 오는 행이 문자열에서 요소로 바뀌 었음을 어떻게 표시하는지 확인합니다 (그리고 문자열을 인쇄하고 요소를 인쇄합니다 , isElement 부울을 인쇄하십시오!) 그리고 추가하려고 할 때 오류는 요소가 아니라는 것입니다. 허프, 퍼프.

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'] 

여기서 문제가 발생합니다.

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 

문제의 근본 원인은 우리의 cElementTree 구현을 혼합하는 것입니다 :

{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] 

Answer 1

I 오류 메시지가이 방법을 재현 할 수 있습니다 :

 #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() 

내 기록이있다 xml.etree.ElementTree 구현이 ElementTree 인 ElementTree입니다. 절대로 두 번 만난다.

수정 사항은 단지 etree과 같이 하나를 선택하고 다른 하나를 모두 바꾸는 것입니다 (예 : ET을 etree으로 바꿉니다).