Update rss_proxy.py
* remove guid rewrite
This commit is contained in:
Slava
@@ -1,116 +1,106 @@
|
|||||||
import html
|
import html
|
||||||
import urllib.parse
|
import urllib.parse
|
||||||
import os
|
import os
|
||||||
import requests
|
import requests
|
||||||
import redis
|
import redis
|
||||||
import xml.etree.ElementTree as ET
|
import xml.etree.ElementTree as ET
|
||||||
import re
|
import re
|
||||||
import unicodedata
|
import unicodedata
|
||||||
from flask import request, Response
|
from flask import request, Response
|
||||||
|
|
||||||
PROXY_URL = os.getenv("PROXY_URL")
|
PROXY_URL = os.getenv("PROXY_URL")
|
||||||
REDIS_URL = os.getenv("REDIS_URL", "redis://localhost:6379/0")
|
REDIS_URL = os.getenv("REDIS_URL", "redis://localhost:6379/0")
|
||||||
CACHE_TTL = int(os.getenv("CACHE_TTL", 3600))
|
CACHE_TTL = int(os.getenv("CACHE_TTL", 3600))
|
||||||
|
|
||||||
rdb = redis.from_url(REDIS_URL)
|
rdb = redis.from_url(REDIS_URL)
|
||||||
|
|
||||||
_head_html = f"""<?xml version="1.0" encoding="UTF-8"?>
|
_head_html = f"""<?xml version="1.0" encoding="UTF-8"?>
|
||||||
<rss version="2.0">
|
<rss version="2.0">
|
||||||
<channel><title>Tapochek.net RSS</title>
|
<channel><title>Tapochek.net RSS</title>
|
||||||
<link>http://tapochek.net/</link>
|
<link>http://tapochek.net/</link>
|
||||||
<ttl>15</ttl>"""
|
<ttl>15</ttl>"""
|
||||||
|
|
||||||
|
|
||||||
def normalize_text(text):
|
def normalize_text(text):
|
||||||
"""Приводит текст к нормальному виду, устраняя странные символы."""
|
"""Приводит текст к нормальному виду, устраняя странные символы."""
|
||||||
if text:
|
if text:
|
||||||
return unicodedata.normalize("NFKC", text)
|
return unicodedata.normalize("NFKC", text)
|
||||||
return text
|
return text
|
||||||
|
|
||||||
|
|
||||||
def extract_viewtopic_link(description):
|
def extract_viewtopic_link(description):
|
||||||
decoded_description = html.unescape(description)
|
decoded_description = html.unescape(description)
|
||||||
match = re.search(r'href="(https?://[^"]+)"', decoded_description)
|
match = re.search(r'href="(https?://[^"]+)"', decoded_description)
|
||||||
return match.group(1) if match else None
|
return match.group(1) if match else None
|
||||||
|
|
||||||
|
|
||||||
def normalize_xml_texts(elem):
|
def normalize_xml_texts(elem):
|
||||||
"""Применяет normalize_text ко всем текстовым узлам XML."""
|
"""Применяет normalize_text ко всем текстовым узлам XML."""
|
||||||
if elem.text:
|
if elem.text:
|
||||||
elem.text = normalize_text(elem.text)
|
elem.text = normalize_text(elem.text)
|
||||||
if elem.tail:
|
if elem.tail:
|
||||||
elem.tail = normalize_text(elem.tail)
|
elem.tail = normalize_text(elem.tail)
|
||||||
for child in elem:
|
for child in elem:
|
||||||
normalize_xml_texts(child)
|
normalize_xml_texts(child)
|
||||||
|
|
||||||
|
|
||||||
def init_proxy(app):
|
def init_proxy(app):
|
||||||
@app.route("/proxy")
|
@app.route("/proxy")
|
||||||
def proxy():
|
def proxy():
|
||||||
"""Proxy RSS feed with per-item caching and GUID replacement."""
|
"""Proxy RSS feed with per-item caching and GUID replacement."""
|
||||||
raw_query = request.query_string.decode()
|
raw_query = request.query_string.decode()
|
||||||
if raw_query.startswith("url="):
|
if raw_query.startswith("url="):
|
||||||
url = urllib.parse.unquote(raw_query[4:])
|
url = urllib.parse.unquote(raw_query[4:])
|
||||||
url = html.unescape(url)
|
url = html.unescape(url)
|
||||||
else:
|
else:
|
||||||
return "Missing URL", 400
|
return "Missing URL", 400
|
||||||
|
|
||||||
try:
|
try:
|
||||||
proxies = {"http": PROXY_URL, "https": PROXY_URL} if PROXY_URL else None
|
proxies = {"http": PROXY_URL, "https": PROXY_URL} if PROXY_URL else None
|
||||||
r = requests.get(url, timeout=10, proxies=proxies)
|
r = requests.get(url, timeout=10, proxies=proxies)
|
||||||
|
|
||||||
xml_data = r.text
|
xml_data = r.text
|
||||||
xml_data = xml_data.replace("&", "&")
|
xml_data = xml_data.replace("&", "&")
|
||||||
_encoding = xml_data.split('encoding="')[1].split('"')[0]
|
_encoding = xml_data.split('encoding="')[1].split('"')[0]
|
||||||
if '<?xml version="1.0" encoding="' in xml_data:
|
if '<?xml version="1.0" encoding="' in xml_data:
|
||||||
xml_data = xml_data.replace(
|
xml_data = xml_data.replace(
|
||||||
f'<?xml version="1.0" encoding="{_encoding}"?>',
|
f'<?xml version="1.0" encoding="{_encoding}"?>',
|
||||||
'<?xml version="1.0" encoding="UTF-8"?>'
|
'<?xml version="1.0" encoding="UTF-8"?>'
|
||||||
)
|
)
|
||||||
|
|
||||||
if '<?xml version="1.0" encoding="UTF-8"?>' not in xml_data:
|
if '<?xml version="1.0" encoding="UTF-8"?>' not in xml_data:
|
||||||
xml_data = f'<?xml version="1.0" encoding="UTF-8"?>{xml_data}'
|
xml_data = f'<?xml version="1.0" encoding="UTF-8"?>{xml_data}'
|
||||||
|
|
||||||
root = ET.fromstring(xml_data)
|
root = ET.fromstring(xml_data)
|
||||||
items = root.findall(".//item")
|
items = root.findall(".//item")
|
||||||
|
|
||||||
cached_items = []
|
cached_items = []
|
||||||
new_items = []
|
new_items = []
|
||||||
|
|
||||||
for item in items:
|
for item in items:
|
||||||
guid = item.find("guid")
|
cache_key = f"rss:item:{guid.text}"
|
||||||
if guid is None or not guid.text:
|
cached_item = rdb.get(cache_key)
|
||||||
continue
|
|
||||||
|
title = item.find("title")
|
||||||
cache_key = f"rss:item:{guid.text}"
|
new_title = re.sub(r'&#\d+', '', title.text)
|
||||||
cached_item = rdb.get(cache_key)
|
title.text = new_title
|
||||||
|
|
||||||
title = item.find("title")
|
if cached_item:
|
||||||
new_title = re.sub(r'&#\d+', '', title.text)
|
cached_items.append(cached_item.decode())
|
||||||
title.text = new_title
|
else:
|
||||||
|
description = item.find("description")
|
||||||
if cached_item:
|
|
||||||
cached_items.append(cached_item.decode())
|
normalize_xml_texts(item)
|
||||||
else:
|
|
||||||
description = item.find("description")
|
item_str = ET.tostring(item, encoding="unicode")
|
||||||
if description is not None:
|
item_str = html.unescape(item_str)
|
||||||
new_guid = extract_viewtopic_link(description.text)
|
rdb.setex(cache_key, CACHE_TTL, item_str)
|
||||||
if new_guid:
|
new_items.append(item_str)
|
||||||
print(f"Заменяю GUID: {guid.text} → {new_guid}")
|
|
||||||
guid.attrib.clear()
|
final_items = cached_items + new_items
|
||||||
guid.text = new_guid
|
response_xml = f"""{_head_html}{"".join(final_items)}</channel></rss>"""
|
||||||
|
|
||||||
normalize_xml_texts(item)
|
return Response(response_xml, content_type="application/xml; charset=utf-8")
|
||||||
|
|
||||||
item_str = ET.tostring(item, encoding="unicode")
|
except Exception as e:
|
||||||
item_str = html.unescape(item_str)
|
return f"Error: {e}", 500
|
||||||
rdb.setex(cache_key, CACHE_TTL, item_str)
|
|
||||||
new_items.append(item_str)
|
|
||||||
|
|
||||||
final_items = cached_items + new_items
|
|
||||||
response_xml = f"""{_head_html}{"".join(final_items)}</channel></rss>"""
|
|
||||||
|
|
||||||
return Response(response_xml, content_type="application/xml; charset=utf-8")
|
|
||||||
|
|
||||||
except Exception as e:
|
|
||||||
return f"Error: {e}", 500
|
|
||||||
|
|||||||
Reference in New Issue
Block a user