From 8c54989f182e2485564a071cbae43afb64cb8905 Mon Sep 17 00:00:00 2001 From: Jan Tuomi Date: Mon, 11 Sep 2023 10:39:36 +0300 Subject: Fix html parsing --- plugins/ScraperSourcePlugin.py | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'plugins/ScraperSourcePlugin.py') diff --git a/plugins/ScraperSourcePlugin.py b/plugins/ScraperSourcePlugin.py index 75aa376..b51943b 100644 --- a/plugins/ScraperSourcePlugin.py +++ b/plugins/ScraperSourcePlugin.py @@ -47,9 +47,7 @@ class Plugin(PluginInterface): result_items: list[Item] = [] with requests.session() as session: page_resp = session.get(self.url, allow_redirects=True) - page_elem = BeautifulSoup( - page_resp.text, features=["xml", "lxml", "lxml-xml"] - ) + page_elem = BeautifulSoup(page_resp.text, "html.parser") post_elems = eval(self.selector_post, {"page": page_elem}) for post_elem in post_elems: @@ -67,7 +65,7 @@ class Plugin(PluginInterface): detail_page_url, allow_redirects=True ) detail_page_elem = BeautifulSoup( - detail_page_resp.text, features=["xml", "lxml", "lxml-xml"] + detail_page_resp.text, "html.parser" ) guid = ItemGUID(detail_page_url, is_perma_link=True) else: -- cgit v1.3