Scrapy, a fast high-level web crawling & scraping framework for Python.
Drop AjaxCrawlMiddleware and escape_ajax().
Andrey Rakhmatullinaf7dcabebb72
diff --git a/docs/topics/settings.rst b/docs/topics/settings.rstindex 84219095b..cf2658d60 100644--- a/docs/topics/settings.rst+++ b/docs/topics/settings.rst@@ -809,7 +809,6 @@ Default:"scrapy.downloadermiddlewares.defaultheaders.DefaultHeadersMiddleware": 400,"scrapy.downloadermiddlewares.useragent.UserAgentMiddleware": 500,"scrapy.downloadermiddlewares.retry.RetryMiddleware": 550,- "scrapy.downloadermiddlewares.ajaxcrawl.AjaxCrawlMiddleware": 560,"scrapy.downloadermiddlewares.redirect.MetaRefreshMiddleware": 580,"scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware": 590,"scrapy.downloadermiddlewares.redirect.RedirectMiddleware": 600,diff --git a/scrapy/downloadermiddlewares/ajaxcrawl.py b/scrapy/downloadermiddlewares/ajaxcrawl.pydeleted file mode 100644index a23deaa45..000000000--- a/scrapy/downloadermiddlewares/ajaxcrawl.py+++ /dev/null@@ -1,114 +0,0 @@-from __future__ import annotations--import logging-import re-from typing import TYPE_CHECKING-from warnings import warn--from w3lib import html--from scrapy.exceptions import NotConfigured, ScrapyDeprecationWarning-from scrapy.http import HtmlResponse, Response-from scrapy.utils.url import escape_ajax--if TYPE_CHECKING:- # typing.Self requires Python 3.11- from typing_extensions import Self-- from scrapy import Request, Spider- from scrapy.crawler import Crawler- from scrapy.settings import BaseSettings---logger = logging.getLogger(__name__)---class AjaxCrawlMiddleware:- """- Handle 'AJAX crawlable' pages marked as crawlable via meta tag.- """-- def __init__(self, settings: BaseSettings):- if not settings.getbool("AJAXCRAWL_ENABLED"):- raise NotConfigured-- warn(- "scrapy.downloadermiddlewares.ajaxcrawl.AjaxCrawlMiddleware is deprecated"- " and will be removed in a future Scrapy version.",- ScrapyDeprecationWarning,- stacklevel=2,- )-- # XXX: Google parses at least first 100k bytes; scrapy's redirect- # middleware parses first 4k. 4k turns out to be insufficient- # for this middleware, and parsing 100k could be slow.- # We use something in between (32K) by default.- self.lookup_bytes: int = settings.getint("AJAXCRAWL_MAXSIZE")-- @classmethod- def from_crawler(cls, crawler: Crawler) -> Self:- return cls(crawler.settings)-- def process_response(- self, request: Request, response: Response, spider: Spider- ) -> Request | Response:- if not isinstance(response, HtmlResponse) or response.status != 200:- return response-- if request.method != "GET":- # other HTTP methods are either not safe or don't have a body- return response-- if "ajax_crawlable" in request.meta: # prevent loops- return response-- if not self._has_ajax_crawlable_variant(response):- return response-- ajax_crawl_request = request.replace(url=escape_ajax(request.url + "#!"))- logger.debug(- "Downloading AJAX crawlable %(ajax_crawl_request)s instead of %(request)s",- {"ajax_crawl_request": ajax_crawl_request, "request": request},- extra={"spider": spider},- )-- ajax_crawl_request.meta["ajax_crawlable"] = True- return ajax_crawl_request-- def _has_ajax_crawlable_variant(self, response: Response) -> bool:- """- Return True if a page without hash fragment could be "AJAX crawlable".- """- body = response.text[: self.lookup_bytes]- return _has_ajaxcrawlable_meta(body)---_ajax_crawlable_re: re.Pattern[str] = re.compile(- r'<meta\s+name=["\']fragment["\']\s+content=["\']!["\']/?>'-)---def _has_ajaxcrawlable_meta(text: str) -> bool:- """- >>> _has_ajaxcrawlable_meta('<html><head><meta name="fragment" content="!"/></head><body></body></html>')- True- >>> _has_ajaxcrawlable_meta("<html><head><meta name='fragment' content='!'></head></html>")- True- >>> _has_ajaxcrawlable_meta('<html><head><!--<meta name="fragment" content="!"/>--></head><body></body></html>')- False- >>> _has_ajaxcrawlable_meta('<html></html>')- False- """-- # Stripping scripts and comments is slow (about 20x slower than- # just checking if a string is in text); this is a quick fail-fast- # path that should work for most pages.- if "fragment" not in text:- return False- if "content" not in text:- return False-- text = html.remove_tags_with_content(text, ("script", "noscript"))- text = html.replace_entities(text)- text = html.remove_comments(text)- return _ajax_crawlable_re.search(text) is not Nonediff --git a/scrapy/settings/default_settings.py b/scrapy/settings/default_settings.pyindex b80e48601..7b54a9c14 100644--- a/scrapy/settings/default_settings.py+++ b/scrapy/settings/default_settings.py@@ -289,7 +289,6 @@ DOWNLOADER_MIDDLEWARES_BASE = {"scrapy.downloadermiddlewares.defaultheaders.DefaultHeadersMiddleware": 400,"scrapy.downloadermiddlewares.useragent.UserAgentMiddleware": 500,"scrapy.downloadermiddlewares.retry.RetryMiddleware": 550,- "scrapy.downloadermiddlewares.ajaxcrawl.AjaxCrawlMiddleware": 560,"scrapy.downloadermiddlewares.redirect.MetaRefreshMiddleware": 580,"scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware": 590,"scrapy.downloadermiddlewares.redirect.RedirectMiddleware": 600,diff --git a/scrapy/utils/url.py b/scrapy/utils/url.pyindex 39b581ff0..1c05ac20e 100644--- a/scrapy/utils/url.py+++ b/scrapy/utils/url.py@@ -9,11 +9,9 @@ import reimport warningsfrom importlib import import_modulefrom typing import TYPE_CHECKING, Any, TypeAlias-from urllib.parse import ParseResult, urldefrag, urlparse, urlunparse-from warnings import warn+from urllib.parse import ParseResult, urlparse, urlunparsefrom w3lib.url import __all__ as _public_w3lib_objects-from w3lib.url import add_or_replace_parameter as _add_or_replace_parameterfrom w3lib.url import any_to_uri as _any_to_urifrom w3lib.url import parse_url as _parse_url@@ -70,39 +68,6 @@ def url_has_any_extension(url: UrlT, extensions: Iterable[str]) -> bool:return any(lowercase_path.endswith(ext) for ext in extensions)-def escape_ajax(url: str) -> str:- """- Return the crawlable url-- >>> escape_ajax("www.example.com/ajax.html#!key=value")- 'www.example.com/ajax.html?_escaped_fragment_=key%3Dvalue'- >>> escape_ajax("www.example.com/ajax.html?k1=v1&k2=v2#!key=value")- 'www.example.com/ajax.html?k1=v1&k2=v2&_escaped_fragment_=key%3Dvalue'- >>> escape_ajax("www.example.com/ajax.html?#!key=value")- 'www.example.com/ajax.html?_escaped_fragment_=key%3Dvalue'- >>> escape_ajax("www.example.com/ajax.html#!")- 'www.example.com/ajax.html?_escaped_fragment_='-- URLs that are not "AJAX crawlable" (according to Google) returned as-is:-- >>> escape_ajax("www.example.com/ajax.html#key=value")- 'www.example.com/ajax.html#key=value'- >>> escape_ajax("www.example.com/ajax.html#")- 'www.example.com/ajax.html#'- >>> escape_ajax("www.example.com/ajax.html")- 'www.example.com/ajax.html'- """- warn(- "escape_ajax() is deprecated and will be removed in a future Scrapy version.",- ScrapyDeprecationWarning,- stacklevel=2,- )- defrag, frag = urldefrag(url)- if not frag.startswith("!"):- return url- return _add_or_replace_parameter(defrag, "_escaped_fragment_", frag[1:])--def add_http_if_no_scheme(url: str) -> str:"""Add http as the default scheme if it is missing from the url."""match = re.match(r"^\w+://", url, flags=re.IGNORECASE)diff --git a/tests/test_downloadermiddleware_ajaxcrawlable.py b/tests/test_downloadermiddleware_ajaxcrawlable.pydeleted file mode 100644index 44084f1e8..000000000--- a/tests/test_downloadermiddleware_ajaxcrawlable.py+++ /dev/null@@ -1,62 +0,0 @@-import pytest--from scrapy.downloadermiddlewares.ajaxcrawl import AjaxCrawlMiddleware-from scrapy.http import HtmlResponse, Request, Response-from scrapy.spiders import Spider-from scrapy.utils.test import get_crawler--[email protected]("ignore::scrapy.exceptions.ScrapyDeprecationWarning")-class TestAjaxCrawlMiddleware:- def setup_method(self):- crawler = get_crawler(Spider, {"AJAXCRAWL_ENABLED": True})- self.spider = crawler._create_spider("foo")- self.mw = AjaxCrawlMiddleware.from_crawler(crawler)-- def _ajaxcrawlable_body(self):- return b'<html><head><meta name="fragment" content="!"/></head><body></body></html>'-- def _req_resp(self, url, req_kwargs=None, resp_kwargs=None):- req = Request(url, **(req_kwargs or {}))- resp = HtmlResponse(url, request=req, **(resp_kwargs or {}))- return req, resp-- def test_non_get(self):- req, resp = self._req_resp("http://example.com/", {"method": "HEAD"})- resp2 = self.mw.process_response(req, resp, self.spider)- assert resp == resp2-- def test_binary_response(self):- req = Request("http://example.com/")- resp = Response("http://example.com/", body=b"foobar\x00\x01\x02", request=req)- resp2 = self.mw.process_response(req, resp, self.spider)- assert resp is resp2-- def test_ajaxcrawl(self):- req, resp = self._req_resp(- "http://example.com/",- {"meta": {"foo": "bar"}},- {"body": self._ajaxcrawlable_body()},- )- req2 = self.mw.process_response(req, resp, self.spider)- assert req2.url == "http://example.com/?_escaped_fragment_="- assert req2.meta["foo"] == "bar"-- def test_ajaxcrawl_loop(self):- req, resp = self._req_resp(- "http://example.com/", {}, {"body": self._ajaxcrawlable_body()}- )- req2 = self.mw.process_response(req, resp, self.spider)- resp2 = HtmlResponse(req2.url, body=resp.body, request=req2)- resp3 = self.mw.process_response(req2, resp2, self.spider)-- assert isinstance(resp3, HtmlResponse), (resp3.__class__, resp3)- assert resp3.request.url == "http://example.com/?_escaped_fragment_="- assert resp3 is resp2-- def test_noncrawlable_body(self):- req, resp = self._req_resp(- "http://example.com/", {}, {"body": b"<html></html>"}- )- resp2 = self.mw.process_response(req, resp, self.spider)- assert resp is resp2