From 339c6f4f3a9d98a66ce8a5625d6a64369e2e0695 Mon Sep 17 00:00:00 2001
From: Mathieu Loiseau <mathieu.loiseau@liris.cnrs.fr>
Date: Fri, 30 Sep 2022 18:15:48 +0200
Subject: [PATCH] begin parsing
---
wikstraktor.py | 43 ++++++++++++++++++++++++++++++++++++++++---
1 file changed, 40 insertions(+), 3 deletions(-)
diff --git a/wikstraktor.py b/wikstraktor.py
index a015d02..50f5c96 100755
--- a/wikstraktor.py
+++ b/wikstraktor.py
@@ -1,7 +1,44 @@
#!/usr/bin/env python3
import pywikibot as pwb
+import wikitextparser as wtp
+
+class Entry:
+ def __init__(self, lemma):
+ self.lemma = lemma
+
+ def __str__(self):
+ res = f"{self.lemma} ({self.cat})"
+
+class Entries:
+ def __init__(self, graphy, languagewiki, languageInWiki):
+ self.language = languageInWiki
+ self.site = pwb.Site(f'wiktionary:{languagewiki}')
+ self.entries = []
+ page = pwb.Page(self.site, graphy)
+ if page.text != "":
+ self.graphy = page.title()
+ wp_content = wtp.parse(page.text)
+ self.parse(wp_content)
+
+ def parse(self, wp_content):
+ sections = wp_content.sections
+ over = False
+ i = 0
+ ### find language
+ while i < len(sections) and not over:
+ over = sections[i].title == self.language
+ i += 1
+ ### language found i points to the first subsection
+ if sections[i].title == "Pronunciation" or sections[i].title == "Pronunciation" :
+ print(sections[i].contents)
+
+ def __str__(self):
+ res = ""
+ for e in self.entries:
+ res += f"{e}\n"
+ return res
if __name__ == "__main__":
- site = pwb.Site('wiktionary:en')
- page = pwb.Page(site, "test")
- print(page.text)
+ e = Entries("test", 'en', "English")
+ #print(e)
+ #Entry("test", wtp.parse(page.text)))
--
GitLab