aboutsummaryrefslogtreecommitdiffstats
path: root/plugins/ScraperSourcePlugin.py
diff options
context:
space:
mode:
authorJan Tuomi <jans.tuomi@gmail.com>2023-09-11 10:39:36 +0300
committerJan Tuomi <jans.tuomi@gmail.com>2023-09-11 10:39:36 +0300
commit8c54989f182e2485564a071cbae43afb64cb8905 (patch)
tree461c0925857039f8f9f3cd56cd9b027ef5e99402 /plugins/ScraperSourcePlugin.py
parenta8aed014dbbfed67ef56fdda6219e7f17922f383 (diff)
Fix html parsing
Diffstat (limited to 'plugins/ScraperSourcePlugin.py')
-rw-r--r--plugins/ScraperSourcePlugin.py6
1 files changed, 2 insertions, 4 deletions
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: