WordPressのアーカイブxmlをHugo用に変換するPythonスクリプト

まずは準備。

code:convertWordPressToHugo.py

# -*- coding: utf-8 -*-

以下は教えてもらった方法をそのまま書いた

code:convertWordPressToHugo.py

import xml.etree.ElementTree as ET

tree = ET.parse("rstylesample.xml")

root = tree.getroot()

# 全ての子要素を取得

for child in root:

print(child)

code:convertWordPressToHugo.py

for child in root:

for childchild in child:

print(childchild)

以下が返ってきた。

<Element 'channel' at 0x109af9a90>

<Element 'title' at 0x109af9ae0>

<Element 'link' at 0x109af9b30>

<Element 'description' at 0x109af9bd0>

<Element 'pubDate' at 0x109af9c20>

<Element 'language' at 0x109af9cc0>

<Element 'generator' at 0x109afc3b0>

<Element 'item' at 0x109afc450>

<Element 'item' at 0x109b2df90>

<Element 'item' at 0x109b346d0>

<Element 'item' at 0x109b39a90>

<Element 'item' at 0x109b41040>

<Element 'item' at 0x109b456d0>

<Element 'item' at 0x109b4adb0>

上の方はR-styleのサイトのデータ。

その下に並んでいるitemが記事リスト。

2023/2/4

タグがitemであるかどうかを知りたい

code:convertWordPressToHugo.py

print(childchild.tag)

以下が返ってきた

title

link

description

pubDate

language

generator

item

item

item

item

item

item

item

code:convertWordPressToHugo.py

if childchild.tag == "item":

print(childchild)

code:old_convertWordPressToHugo.py

for topic in childchild:

if (topic.tag == "title"):

print(topic.text)

さらに中身を探索

code:old_2convertWordPressToHugo.py

for topic in childchild:

print(topic.tag)

if (topic.tag == "title"):

print(topic.text)

if (topic.tag == "pubDate"):

print(topic.text)

if (topic.tag == "content:encoded"):

print(topic.text)

print(topic.text)

code:old_3convertWordPressToHugo.py

if childchild.tag == "item":

temphead = []

tempbody = ""

temphead.append(sectionline)

for topic in childchild:

if (topic.tag == "title"):

temphead.append("title: " +topic.text)

if (topic.tag == "pubDate"):

temphead.append("date: " +topic.text)

tempbody = topic.text

else:

temphead.append("draft: false")

temphead.append(sectionline)

temp = "\n".join(temphead) + "\n\n" + tempbody

with open(targetFilePath,mode="w") as f:

f.write(temp)

print("ファイルを作成しました")

code:convertWordPressToHugo.py

if childchild.tag == "item":

temphead = []

tempbody = ""

tempCat = []

tempTag = []

temphead.append(sectionline)

for topic in childchild:

if (topic.tag == "title"):

temphead.append("title : " +topic.text)

if (topic.tag == "pubDate"):

temphead.append("date : " +topic.text)

if (topic.tag == "link"):

tempbody = topic.text

else:

temphead.append("draft : false")

temphead.append("author : 倉下忠憲")

temphead.append(sectionline)

temp = "\n".join(temphead) + "\n\n" + tempbody

with open(targetFilePath,mode="w") as f:

f.write(temp)

print("ファイルを作成しました")

概ねの完成版

code:fixconvertWordPressToHugo.py

# -*- coding: utf-8 -*-

import xml.etree.ElementTree as ET

import urllib.parse

tree = ET.parse("r-style.xml")

root = tree.getroot()

# 全ての子要素を取得

for child in root:

pass

for child in root:

for childchild in child:

if childchild.tag == "item":

temphead = []

tempbody = ""

tempCat = []

tempTag = []

temphead.append(sectionline)

for topic in childchild:

if (topic.tag == "title"):

if topic.text is not None:

artcleTitle = topic.text.replace("/","／")

else:

artcleTitle = "無題"

temphead.append("title : " +artcleTitle)

if (topic.tag == "pubDate"):

if topic.text is not None:

temphead.append("date : " +topic.text)

else:

temphead.append("date : " +"Wed, 01 Mar 2000 00:00:00 +0000")

if (topic.tag == "link"):

if topic.text is not None:

tempbody = topic.text

else:

tempbody = "中身なし"

else:

temphead.append("draft : false")

temphead.append("author : 倉下忠憲")

temphead.append(sectionline)

temp = "\n".join(temphead) + "\n\n" + tempbody

with open("contents/" + targetFilePath,mode="w") as f:

f.write(temp)

print("ファイルを作成しました")