lee/changedetection.io
1
0
Fork 0
mirror of https://github.com/dgtlmoon/changedetection.io.git synced 2026-09-25 23:06:51 +00:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity

remove unused types

Browse Source
This commit is contained in:
dgtlmoon
2025-10-09 10:48:48 +02:00
parent 2e31a1a36e
commit 871466ce37
1 changed files with 0 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
changedetectionio/processors/magic.py
-21
View File
@@ -35,11 +35,6 @@ JSON_CONTENT_TYPES = [
"application/vnd.api+json",
]
# CSV Content-types
CSV_CONTENT_TYPES = [
"text/csv",
"application/csv",
]
# Generic XML Content-types (non-RSS/Atom)
XML_CONTENT_TYPES = [
@@ -47,14 +42,6 @@ XML_CONTENT_TYPES = [
"application/xml",
]
# YAML Content-types
YAML_CONTENT_TYPES = [
"text/yaml",
"text/x-yaml",
"application/yaml",
"application/x-yaml",
]
HTML_PATTERNS = ['<!doctype html', '<html', '<head', '<body', '<script', '<iframe', '<div']
import re
@@ -108,15 +95,10 @@ class guess_stream_type():
self.is_rss = True
elif any(s in http_content_header for s in JSON_CONTENT_TYPES):
self.is_json = True
elif any(s in http_content_header for s in CSV_CONTENT_TYPES):
self.is_csv = True
elif any(s in http_content_header for s in XML_CONTENT_TYPES):
# Only mark as generic XML if not already detected as RSS
if not self.is_rss:
self.is_xml = True
elif any(s in http_content_header for s in YAML_CONTENT_TYPES) or any(s in magic_content_header for s in YAML_CONTENT_TYPES):
self.is_yaml = True
self.is_plaintext = True # We dont have any other support
elif 'pdf' in magic_content_header:
self.is_pdf = True
###
@@ -128,9 +110,6 @@ class guess_stream_type():
logger.debug(f"Trusting magic's text/plain result (no HTML patterns detected)")
elif any(s in magic_content_header for s in JSON_CONTENT_TYPES):
self.is_json = True
elif any(s in magic_content_header for s in CSV_CONTENT_TYPES):
self.is_csv = True
self.is_plaintext = True # We dont have any other support
# magic will call a rss document 'xml'
elif '<rss' in test_content_normalized or '<feed' in test_content_normalized or any(s in magic_content_header for s in RSS_XML_CONTENT_TYPES):
self.is_rss = True