ichthyo/wegen
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Experiment: Inhalte aus SoSci-XML extrahieren

Browse source 
- CDATA ist kein Problem
- Eingeschachtelte Elemene parsen
- XML-unquoting
This commit is contained in:
Fischlurch 2023-05-18 22:29:00 +02:00
parent a26bd9f133
commit 0ddd39a576
3 changed files with 109 additions and 20 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
sosci2word/_README.txt
View file

@ -77,7 +77,9 @@ NOTE: es ist mit den gegebenen Mitteln nicht möglich, das Tabellen-Styling zu s
Verarbeitungs-Schema
~~~~~~~~~~~~~~~~~~~~
[yellow-background]#(dies ist der Plan zur Implementierung)#:
Fragebogen-Definitionen können mit der Mini-DOM-Library gelesen werden, das Word-Dokument mit python-docx.
Fragebogen-Definitionen können mit https://docs.python.org/3/library/xml.etree.elementtree.html[Elementtree]
aus der Python-Standard-Library gelesen werden, das Word-Dokument mit
https://python-docx.readthedocs.io/en/latest/index.html[python-docx(Documentation)].
Die Verarbeitung untergliedert sich in drei Phasen:
1. SoSci-Definitionen einlesen

102
sosci2word/_SoSci2Word.mm
View file

@ -61,8 +61,8 @@
</node>
</node>
</node>
<node BACKGROUND_COLOR="#eef0c5" COLOR="#990000" CREATED="1684368494840" ID="ID_1680262238" MODIFIED="1684377529586" POSITION="right" TEXT="Vor-Analyse (Hermann)">
<icon BUILTIN="pencil"/>
<node COLOR="#338800" CREATED="1684368494840" ID="ID_1680262238" MODIFIED="1684448582270" POSITION="right" TEXT="Vor-Analyse (Hermann)">
<icon BUILTIN="button_ok"/>
<node CREATED="1684377232205" ID="ID_1958647529" MODIFIED="1684377240495" TEXT="Word-Dokument">
<node COLOR="#435e98" CREATED="1684377241659" ID="ID_211996471" MODIFIED="1684438272776" TEXT="Analyse">
<icon BUILTIN="info"/>
@ -167,7 +167,7 @@
</node>
</node>
<node CREATED="1684425093938" ID="ID_983214559" MODIFIED="1684425101437" TEXT="SoSci-XML">
<node BACKGROUND_COLOR="#eee5c3" COLOR="#990000" CREATED="1684425106925" ID="ID_1986143984" MODIFIED="1684425619449" TEXT="Analyse">
<node COLOR="#435e98" CREATED="1684425106925" ID="ID_1986143984" MODIFIED="1684448071529" TEXT="Analyse">
<icon BUILTIN="info"/>
<node CREATED="1684425112703" ID="ID_1200576100" MODIFIED="1684425122363" TEXT="folgt grunds&#xe4;tzlich dem Aufbau der Web-Oberfl&#xe4;che"/>
<node CREATED="1684425125074" ID="ID_590581145" MODIFIED="1684425134221" TEXT="spezieller Twist">
@ -178,13 +178,20 @@
<icon BUILTIN="messagebox_warning"/>
</node>
</node>
<node BACKGROUND_COLOR="#eee5c3" COLOR="#990000" CREATED="1684425545402" ID="ID_678326426" MODIFIED="1684425580894" TEXT="Experimente">
<icon BUILTIN="flag-yellow"/>
<node BACKGROUND_COLOR="#eee5c3" COLOR="#990000" CREATED="1684425550850" ID="ID_53111427" MODIFIED="1684425577526" TEXT="CDATA aus XML holen">
<icon BUILTIN="flag-yellow"/>
<node COLOR="#338800" CREATED="1684425545402" ID="ID_678326426" MODIFIED="1684448051586" TEXT="Experimente">
<icon BUILTIN="button_ok"/>
<node COLOR="#338800" CREATED="1684425550850" ID="ID_53111427" MODIFIED="1684448039373" TEXT="CDATA aus XML holen">
<icon BUILTIN="button_ok"/>
</node>
<node BACKGROUND_COLOR="#eee5c3" COLOR="#990000" CREATED="1684425555507" ID="ID_1704018761" MODIFIED="1684425576097" TEXT="unquote char-Content">
<icon BUILTIN="flag-yellow"/>
<node COLOR="#338800" CREATED="1684425555507" ID="ID_1704018761" MODIFIED="1684448041439" TEXT="unquote char-Content">
<icon BUILTIN="button_ok"/>
</node>
<node COLOR="#338800" CREATED="1684448042131" ID="ID_1128616077" MODIFIED="1684448050607" TEXT="&#xfc;ber alle Pages im Questionaire iterieren">
<icon BUILTIN="button_ok"/>
</node>
<node BACKGROUND_COLOR="#e0ceaa" COLOR="#690f14" CREATED="1684448052898" ID="ID_463103903" MODIFIED="1684448065709" TEXT="alles easy">
<font ITALIC="true" NAME="SansSerif" SIZE="12"/>
<icon BUILTIN="ksmiletris"/>
</node>
</node>
</node>
@ -236,7 +243,7 @@
<node CREATED="1684368381438" ID="ID_536028682" MODIFIED="1684368562213" POSITION="left" TEXT="Word verstehen">
<font NAME="SansSerif" SIZE="16"/>
<icon BUILTIN="idea"/>
<node CREATED="1684371396181" ID="ID_1494643844" MODIFIED="1684371402030" TEXT="ein Wort-Dokument">
<node CREATED="1684371396181" FOLDED="true" ID="ID_1494643844" MODIFIED="1684448318966" TEXT="ein Wort-Dokument....">
<node CREATED="1684371402940" ID="ID_775127417" MODIFIED="1684371610767" TEXT="is a ZIP-compressed folder">
<node CREATED="1684371633747" ID="ID_315178960" MODIFIED="1684371642943" TEXT="holds ressources"/>
<node CREATED="1684371709763" ID="ID_703260300" MODIFIED="1684371713790" TEXT="+ metadata"/>
@ -249,7 +256,8 @@
<node CREATED="1684371734712" ID="ID_1561962743" MODIFIED="1684371745264" TEXT="holds metadata"/>
<node CREATED="1684371745750" ID="ID_1039576961" MODIFIED="1684371749874" TEXT="+ actual content"/>
</node>
<node CREATED="1684371422890" ID="ID_546163362" MODIFIED="1684371752987" TEXT="actual Content">
<node CREATED="1684371422890" FOLDED="true" ID="ID_546163362" MODIFIED="1684448225501" TEXT="actual Content">
<icon BUILTIN="back"/>
<node CREATED="1684371432720" ID="ID_1123773556" MODIFIED="1684371453578" TEXT="a sequence of Paragraphs"/>
<node CREATED="1684372227175" ID="ID_821942243" MODIFIED="1684372243007" TEXT="(or other block-level elements)">
<richcontent TYPE="NOTE"><html>
@ -310,7 +318,12 @@
<node CREATED="1684368386013" ID="ID_271244982" MODIFIED="1684368562213" POSITION="left" TEXT="Python verstehen">
<font NAME="SansSerif" SIZE="16"/>
<icon BUILTIN="idea"/>
<node COLOR="#435e98" CREATED="1684369795005" ID="ID_1730265194" MODIFIED="1684369882498">
<node COLOR="#435e98" CREATED="1684369795005" ID="ID_1730265194" MODIFIED="1684448581378" TEXT="Libraries">
<edge COLOR="#5856c4" STYLE="linear"/>
<cloud COLOR="#ccd0eb"/>
<font NAME="SansSerif" SIZE="16"/>
<icon BUILTIN="info"/>
<node COLOR="#435e98" CREATED="1684444895031" ID="ID_24582245" MODIFIED="1684444920548">
<richcontent TYPE="NODE"><html>
<head>
@ -320,15 +333,66 @@
Modul <b>python-doxc</b>
</p>
</body>
</html></richcontent>
<edge COLOR="#5856c4" STYLE="linear"/>
<cloud COLOR="#ccd0eb"/>
<font NAME="SansSerif" SIZE="14"/>
</html>
</richcontent>
<node CREATED="1684369841851" ID="ID_82528903" MODIFIED="1684444929524" TEXT="Doku">
<icon BUILTIN="info"/>
<node CREATED="1684369841851" ID="ID_1686589099" MODIFIED="1684369845472" TEXT="Doku">
<node CREATED="1684369895137" ID="ID_775368900" LINK="https://pypi.org/project/python-docx/" MODIFIED="1684369900089" TEXT="pypi.org"/>
<node CREATED="1684369901112" ID="ID_1856977529" MODIFIED="1684369907713" TEXT="readthedoks"/>
</node>
<node CREATED="1684448124993" ID="ID_1207539182" MODIFIED="1684448134499" TEXT="Standardf&#xe4;lle">
<icon BUILTIN="idea"/>
<node CREATED="1684448136157" ID="ID_1685757847" MODIFIED="1684448149185" TEXT="document.add_paragraph(&lt;text&gt;, style=&lt;stylename&gt;)"/>
<node CREATED="1684448160291" ID="ID_1014538985" LINK="#ID_1369606274" MODIFIED="1684448204907" TEXT="Stylenamen werden in sichtbare Form &#xfc;bersetzt"/>
<node CREATED="1684448234489" ID="ID_746702681" MODIFIED="1684448273543" TEXT="paragraph.text (Read/Write)">
<richcontent TYPE="NOTE"><html>
<head>
</head>
<body>
<p>
Beim Schreiben wird der bestehende Content verworfen und durch einen einzigen Run ersetzt, der den gegebenen Text ohne weitere Formatierungen enth&#228;lt
</p>
</body>
</html>
</richcontent>
</node>
</node>
</node>
<node COLOR="#435e98" CREATED="1684444938400" ID="ID_1803428220" MODIFIED="1684444952121">
<richcontent TYPE="NODE"><html>
<head>
</head>
<body>
<p>
Modul <b>elementtree</b>
</p>
</body>
</html>
</richcontent>
<node CREATED="1684444953007" ID="ID_1528197614" LINK="https://docs.python.org/3/library/xml.etree.elementtree.html" MODIFIED="1684444976183" TEXT="Doku">
<icon BUILTIN="info"/>
<node CREATED="1684369895137" ID="ID_1453810450" LINK="https://pypi.org/project/python-docx/" MODIFIED="1684369900089" TEXT="pypi.org"/>
<node CREATED="1684369901112" ID="ID_1354824178" MODIFIED="1684369907713" TEXT="readthedoks"/>
</node>
<node CREATED="1684445181761" ID="ID_51292475" MODIFIED="1684445193504" TEXT="CDATA-Inhalt wird direkt unterst&#xfc;tzt">
<icon BUILTIN="idea"/>
</node>
<node CREATED="1684445195526" ID="ID_838670695" MODIFIED="1684445219368" TEXT="unescape">
<node CREATED="1684445240208" ID="ID_1228520062" LINK="https://stackoverflow.com/a/54788611" MODIFIED="1684445249673" TEXT="direkt per html.unescape"/>
<node CREATED="1684445266182" ID="ID_40459638" MODIFIED="1684445290580">
<richcontent TYPE="NODE"><html>
<head>
</head>
<body>
<pre http-equiv="content-type" content="text/html; charset=utf-8" class="default s-code-block"><code class="hljs language-coffeescript">&gt;&gt;&gt; from html import unescape
&gt;&gt;&gt; unescape('&amp;quot;')
'&quot;'</code></pre>
</body>
</html>
</richcontent>
</node>
</node>
</node>
</node>
</node>

23
sosci2word/experiment2.py Executable file
View file

@ -0,0 +1,23 @@
#!/usr/bin/python3
from xml.etree import ElementTree
root = ElementTree.parse('ThesisFragebogen.2023-04-19.xml').getroot()
layout = root.find('surveyLayout').find('template')
print(layout.text)
quest = root.find('questionnaire').find('attributes.specific')
quest = next(a for a in quest.findall('attr') if a.get('id') == 'content')
print(quest.text)
questRoot = ElementTree.fromstring(quest.text)
for page in questRoot.findall('page'):
info = page.find('info')
if info != None:
print(info.text)
for quest in page.findall('question'):
print(quest.get('id'))