Python lxml iterparse сортировка по атрибуту большого файла xml - PullRequest
1 голос
/ 22 октября 2019

У меня большой XML-файл, который я пытаюсь упорядочить значки для каждой программы, я хочу упорядочить значки по убыванию значения в атрибуте width, мне удалось удалить некоторые значки, которые не нужныно я не уверен, как я могу заказать значки, любая помощь будет высоко ценится.

Вот код, который я использую, чтобы удалить значок, который мне не нужен, но я не уверен, как я могу затем заказать их. Я использую iterparse, так как чтение всего файла занимает много памяти.

Текущий код для удаления:

import lxml.etree as ET
xml_source = 'ss_sky_sw_xmltv.xml'
xml_output = 'ss_sky_sw_xmltv_parsed.xml'

context = ET.iterparse(xml_source, encoding='iso-8859-1', tag='icon')
for event, elem in context:
    if elem.getparent().tag != 'channel' :
        if elem.tag == 'icon':
            if elem.attrib['width'] == '180' and elem.attrib['height'] == '135':
                elem.getparent().remove(elem)
            elif elem.attrib['width'] == '120' and elem.attrib['height'] == '180':
                elem.getparent().remove(elem)
ET.ElementTree(context.root).write(xml_output, xml_declaration=True)

XML-файл:

<tv source-info-name="Schedules Direct" generator-info-name="mc2xml" generator-info-url="mailto:mc2xml@gmail.com">
    <channel id="I963.24337.schedulesdirect.org">
        <display-name>963 BBC1SE</display-name>
        <display-name>963</display-name>
        <display-name>BBC1SE</display-name>
        <display-name>BBC One South East</display-name>
        <display-name>BBC1</display-name>
        <icon src="https://s3.amazonaws.com/schedulesdirect/assets/stationLogos/s24337_h3_aa.png" width="360" height="270" />
    </channel>
    <channel id="I964.24326.schedulesdirect.org">
        <display-name>964 BBC1STH</display-name>
        <display-name>964</display-name>
        <display-name>BBC1STH</display-name>
        <display-name>BBC One South</display-name>
        <display-name>BBC1</display-name>
        <icon src="https://s3.amazonaws.com/schedulesdirect/assets/stationLogos/s24326_h3_aa.png" width="360" height="270" />
    </channel>
    <programme start="20191007150000 +0100" stop="20191007154500 +0100" channel="I101.24327.schedulesdirect.org">
        <title lang="en">Escape to the Perfect Town</title>
        <sub-title lang="en">Knaresborough, North Yorkshire</sub-title>
        <desc lang="en">Steve Brown helps a couple feeling the pinch of the London property market to decide on their perfect town and the right property in which to raise their young children. They're amazed by what their £280,000 budget can buy them out of the capital city, and that moving to a desirable town means buzzing high streets, great community spirit and green spaces, as well as a quick commute to York for a teaching job is all on their doorstep.</desc>
        <credits>
            <producer>John Comerford</producer>
            <producer>Eleanor Brocklehurst</producer>
        </credits>
        <date>20191007</date>
        <category lang="en">House/garden</category>
        <category lang="en">Home improvement</category>
        <icon src="https://json.schedulesdirect.org/20141201/image/assets/p17421608_st_v6_aa.jpg" width="120" height="180" />
        <icon src="https://json.schedulesdirect.org/20141201/image/assets/p17421608_st_v2_aa.jpg" width="135" height="180" />
        <icon src="https://json.schedulesdirect.org/20141201/image/assets/p17421608_st_h5_aa.jpg" width="180" height="135" />
        <icon src="https://json.schedulesdirect.org/20141201/image/assets/p17421608_st_h14_aa.jpg" width="240" height="135" />
        <icon src="https://s3.amazonaws.com/schedulesdirect/assets/p17421608_st_v5_aa.jpg" width="240" height="360" />
        <icon src="https://s3.amazonaws.com/schedulesdirect/assets/p17421608_st_v3_aa.jpg" width="270" height="360" />
        <icon src="https://s3.amazonaws.com/schedulesdirect/assets/p17421608_st_h3_aa.jpg" width="360" height="270" />
        <icon src="https://json.schedulesdirect.org/20141201/image/assets/p17421608_st_h13_aa.jpg" width="480" height="270" />
        <icon src="https://s3.amazonaws.com/schedulesdirect/assets/p17421608_st_v7_aa.jpg" width="480" height="720" />
        <icon src="https://json.schedulesdirect.org/20141201/image/assets/p17421608_st_v4_aa.jpg" width="540" height="720" />
        <icon src="https://json.schedulesdirect.org/20141201/image/assets/p17421608_st_h6_aa.jpg" width="720" height="540" />
        <icon src="https://s3.amazonaws.com/schedulesdirect/assets/p17421608_st_h12_aa.jpg" width="960" height="540" />
        <icon src="https://s3.amazonaws.com/schedulesdirect/assets/p17421608_st_h11_aa.jpg" width="1280" height="720" />
        <icon src="https://s3.amazonaws.com/schedulesdirect/assets/p17421608_st_v8_aa.jpg" width="960" height="1440" />
        <icon src="https://json.schedulesdirect.org/20141201/image/assets/p17421608_st_v9_aa.jpg" width="1080" height="1440" />
        <icon src="https://json.schedulesdirect.org/20141201/image/assets/p17421608_st_h9_aa.jpg" width="1440" height="1080" />
        <icon src="https://s3.amazonaws.com/schedulesdirect/assets/p17421608_st_h10_aa.jpg" width="1920" height="1080" />
        <icon src="https://json.schedulesdirect.org/20141201/image/assets/p17421608_st_h2_aa.jpg" width="2048" height="1024" />
        <episode-num system="dd_progid">EP03325404.0001</episode-num>
        <episode-num system="xmltv_ns">0.0.</episode-num>
        <new />
    </programme>
    <programme start="20191007154500 +0100" stop="20191007163000 +0100" channel="I101.24327.schedulesdirect.org">
        <title lang="en">Make Me a Dealer</title>
        <sub-title lang="en">Liverpool: Sarah &amp; Marika</sub-title>
        <desc lang="en">Paul Martin teaches two antiques lovers the tricks of the trade and turns them into successful antiques dealers. In Liverpool, hairdresser Sarah faces off against civil servant Marika.</desc>
        <credits>
            <director>Gabe Crozier</director>
            <director>Dan Donnelly</director>
            <producer>Paul Tucker</producer>
            <producer>Carole Lochhead</producer>
            <producer>Jo Dunscombe</producer>
            <presenter>Paul Martin</presenter>
        </credits>
        <date>20191007</date>
        <category lang="en">How-to</category>
        <category lang="en">Collectibles</category>
        <category lang="en">Art</category>
        <category lang="en">Arts/crafts</category>
        <icon src="https://s3.amazonaws.com/schedulesdirect/assets/p16172084_b_v6_aa.jpg" width="120" height="180" />
        <icon src="https://json.schedulesdirect.org/20141201/image/assets/p16172084_b_v2_aa.jpg" width="135" height="180" />
        <icon src="https://json.schedulesdirect.org/20141201/image/assets/p16172084_b_h5_aa.jpg" width="180" height="135" />
        <icon src="https://json.schedulesdirect.org/20141201/image/assets/p16172084_b_h14_aa.jpg" width="240" height="135" />
        <icon src="https://s3.amazonaws.com/schedulesdirect/assets/p16172084_b_v5_aa.jpg" width="240" height="360" />
        <icon src="https://s3.amazonaws.com/schedulesdirect/assets/p16172084_b_v3_aa.jpg" width="270" height="360" />
        <icon src="https://s3.amazonaws.com/schedulesdirect/assets/p16172084_b_h3_aa.jpg" width="360" height="270" />
        <icon src="https://s3.amazonaws.com/schedulesdirect/assets/p16172084_b_h13_aa.jpg" width="480" height="270" />
        <icon src="https://s3.amazonaws.com/schedulesdirect/assets/p16172084_b_v7_aa.jpg" width="480" height="720" />
        <icon src="https://json.schedulesdirect.org/20141201/image/assets/p16172084_b_v4_aa.jpg" width="540" height="720" />
        <icon src="https://json.schedulesdirect.org/20141201/image/assets/p16172084_b_h6_aa.jpg" width="720" height="540" />
        <icon src="https://s3.amazonaws.com/schedulesdirect/assets/p16172084_b_h12_aa.jpg" width="960" height="540" />
        <icon src="https://json.schedulesdirect.org/20141201/image/assets/p16172084_b_h11_aa.jpg" width="1280" height="720" />
        <icon src="https://s3.amazonaws.com/schedulesdirect/assets/p16172084_b_v8_aa.jpg" width="960" height="1440" />
        <icon src="https://json.schedulesdirect.org/20141201/image/assets/p16172084_b_v9_aa.jpg" width="1080" height="1440" />
        <icon src="https://s3.amazonaws.com/schedulesdirect/assets/p16172084_b_h9_aa.jpg" width="1440" height="1080" />
        <icon src="https://s3.amazonaws.com/schedulesdirect/assets/p16172084_b_h10_aa.jpg" width="1920" height="1080" />
        <icon src="https://s3.amazonaws.com/schedulesdirect/assets/p16172084_b_v12_aa.jpg" width="1920" height="2880" />
        <icon src="https://json.schedulesdirect.org/20141201/image/assets/p16172084_b_v13_aa.jpg" width="2160" height="2880" />
        <icon src="https://json.schedulesdirect.org/20141201/image/assets/p16172084_b_s4_aa.jpg" width="3000" height="3000" />
        <episode-num system="dd_progid">EP03082486.0021</episode-num>
        <episode-num system="xmltv_ns">1.0.</episode-num>
        <new />
    </programme>
</tv>

1 Ответ

0 голосов
/ 23 октября 2019
import lxml.etree as ET
from copy import deepcopy

xml_source = 'ss_sky_sw_xmltv.xml'
xml_output = 'ss_sky_sw_xmltv_parsed.xml'
# icons with these dimensions (width, height) will be removed:
remove_dimensions = (
    (180, 135),
    (120, 180),
    )

tree = ET.parse(xml_source)
root = tree.getroot()
for programme in root.iterfind('programme'):
    # Create copy of all icons to reinsert them in the right order
    icons = deepcopy(sorted(programme.findall('icon'), key=lambda x: int(x.attrib['height'])))
    # Remove all icons from programme
    for old_icon in programme.findall('icon'):
        programme.remove(old_icon)

    # Reinsert the items
    for new_icon in icons:
        # Create a dict to compare
        dimensions = int(new_icon.attrib['width']), int(new_icon.attrib['height'])
        # Compare the dict if it should be removed (not included again)
        if dimensions not in remove_dimensions:
            programme.append(new_icon)

# Save the file
tree.write(xml_output, xml_declaration=True, pretty_print=True)
...