From 1f08432fbf416d18b317ae7c8e1fb0cca7dbe8c5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Micha=C5=82=20Koz=C5=82owski?=
 <michalkozlowski936@gmail.com>
Date: Sat, 7 Jan 2023 14:59:07 +0100
Subject: [PATCH] crawler fix

---
 crawler.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/crawler.py b/crawler.py
index dcc639a..7cfbdad 100644
--- a/crawler.py
+++ b/crawler.py
@@ -11,7 +11,7 @@ MAIN_URL = "https://pl.wikisource.org/"
 def get_page_data(page_element):
         time.sleep(0.5)
         doc = requests.get(MAIN_URL + page_element['href'])
-        doc_soup = BeautifulSoup(doc.text, 'lxml', from_encoding="utf-8")
+        doc_soup = BeautifulSoup(doc.text, 'lxml')
         text = doc_soup.find("div", {"class": "pagetext"}).next_element
         image_url = doc_soup.find("div", {"class": "prp-page-image"}).next_element['src']
         return {"title": page_element['title'], "href": MAIN_URL + page_element['href'], "image_url": image_url, "text": text.text}