aio-scrapy 2.1.3__py3-none-any.whl → 2.1.6__py3-none-any.whl

aioscrapy/utils/url.py

@@ -1,9 +1,17 @@
 """
+URL utility functions for aioscrapy.
+aioscrapy的URL实用函数。
+
 This module contains general purpose URL functions not found in the standard
-library.
+library. It provides utilities for URL parsing, manipulation, and validation
+specific to web crawling needs.
+此模块包含标准库中没有的通用URL函数。
+它提供了特定于网络爬取需求的URL解析、操作和验证实用工具。
 
 Some of the functions that used to be imported from this module have been moved
 to the w3lib.url module. Always import those from there instead.
+以前从此模块导入的一些函数已移至w3lib.url模块。
+始终从那里导入这些函数。
 """
 import posixpath
 import re
@@ -11,72 +19,242 @@ from urllib.parse import ParseResult, urldefrag, urlparse, urlunparse
 
 # scrapy.utils.url was moved to w3lib.url and import * ensures this
 # move doesn't break old code
-from w3lib.url import *
+from w3lib.url import *  # This imports functions like any_to_uri, add_or_replace_parameter, etc.
 from w3lib.url import _safe_chars, _unquotepath  # noqa: F401
 from aioscrapy.utils.python import to_unicode
 
 
 def url_is_from_any_domain(url, domains):
-    """Return True if the url belongs to any of the given domains"""
+    """
+    Check if a URL belongs to any of the given domains.
+    检查URL是否属于给定域名中的任何一个。
+
+    This function checks if the host part of the URL exactly matches any of the
+    given domains, or if it is a subdomain of any of them. The comparison is
+    case-insensitive.
+    此函数检查URL的主机部分是否与给定域名中的任何一个完全匹配，
+    或者它是否是其中任何一个的子域。比较不区分大小写。
+
+    Args:
+        url: The URL to check. Can be a string or a ParseResult object.
+             要检查的URL。可以是字符串或ParseResult对象。
+        domains: A list of domain names to check against.
+                要检查的域名列表。
+
+    Returns:
+        bool: True if the URL belongs to any of the given domains, False otherwise.
+              如果URL属于给定域名中的任何一个，则为True，否则为False。
+
+    Examples:
+        >>> url_is_from_any_domain("http://www.example.com/some/page.html", ["example.com"])
+        True
+        >>> url_is_from_any_domain("http://sub.example.com/", ["example.com"])
+        True
+        >>> url_is_from_any_domain("http://example.org/", ["example.com"])
+        False
+    """
+    # Get the host part of the URL and convert to lowercase
+    # 获取URL的主机部分并转换为小写
     host = parse_url(url).netloc.lower()
+
+    # If there's no host, it's not from any domain
+    # 如果没有主机，则不属于任何域名
     if not host:
         return False
+
+    # Convert all domains to lowercase for case-insensitive comparison
+    # 将所有域名转换为小写以进行不区分大小写的比较
     domains = [d.lower() for d in domains]
+
+    # Check if the host exactly matches any domain or is a subdomain of any domain
+    # 检查主机是否与任何域名完全匹配或是任何域名的子域
     return any((host == d) or (host.endswith(f'.{d}')) for d in domains)
 
 
 def url_is_from_spider(url, spider):
-    """Return True if the url belongs to the given spider"""
+    """
+    Check if a URL belongs to the given spider.
+    检查URL是否属于给定的爬虫。
+
+    This function checks if the URL belongs to the domains that the spider
+    is allowed to crawl. It considers both the spider's name and its
+    'allowed_domains' attribute (if it exists).
+    此函数检查URL是否属于爬虫允许爬取的域名。
+    它同时考虑爬虫的名称和其'allowed_domains'属性（如果存在）。
+
+    Args:
+        url: The URL to check. Can be a string or a ParseResult object.
+             要检查的URL。可以是字符串或ParseResult对象。
+        spider: The spider object to check against.
+               要检查的爬虫对象。
+
+    Returns:
+        bool: True if the URL belongs to the spider's domains, False otherwise.
+              如果URL属于爬虫的域名，则为True，否则为False。
+    """
+    # Check if the URL belongs to either the spider's name or any of its allowed domains
+    # 检查URL是否属于爬虫的名称或其任何允许的域名
     return url_is_from_any_domain(url, [spider.name] + list(getattr(spider, 'allowed_domains', [])))
 
 
 def url_has_any_extension(url, extensions):
+    """
+    Check if a URL has any of the given extensions.
+    检查URL是否具有给定扩展名中的任何一个。
+
+    This function extracts the file extension from the URL path and checks
+    if it matches any of the provided extensions. The comparison is case-insensitive.
+    此函数从URL路径中提取文件扩展名，并检查它是否与提供的任何扩展名匹配。
+    比较不区分大小写。
+
+    Args:
+        url: The URL to check. Can be a string or a ParseResult object.
+             要检查的URL。可以是字符串或ParseResult对象。
+        extensions: A list of file extensions to check against (including the dot).
+                   要检查的文件扩展名列表（包括点）。
+
+    Returns:
+        bool: True if the URL has any of the given extensions, False otherwise.
+              如果URL具有给定扩展名中的任何一个，则为True，否则为False。
+
+    Examples:
+        >>> url_has_any_extension("http://example.com/file.pdf", ['.pdf', '.doc'])
+        True
+        >>> url_has_any_extension("http://example.com/file.PDF", ['.pdf'])
+        True
+        >>> url_has_any_extension("http://example.com/file.txt", ['.pdf', '.doc'])
+        False
+    """
+    # Extract the file extension from the URL path and check if it's in the list
+    # 从URL路径中提取文件扩展名，并检查它是否在列表中
     return posixpath.splitext(parse_url(url).path)[1].lower() in extensions
 
 
 def parse_url(url, encoding=None):
-    """Return urlparsed url from the given argument (which could be an already
-    parsed url)
     """
+    Parse a URL into its components.
+    将URL解析为其组成部分。
+
+    This function parses a URL into its components using urllib.parse.urlparse.
+    If the input is already a ParseResult object, it is returned unchanged.
+    If the input is a string or bytes, it is first converted to unicode.
+    此函数使用urllib.parse.urlparse将URL解析为其组成部分。
+    如果输入已经是ParseResult对象，则原样返回。
+    如果输入是字符串或字节，则首先将其转换为unicode。
+
+    Args:
+        url: The URL to parse. Can be a string, bytes, or ParseResult object.
+             要解析的URL。可以是字符串、字节或ParseResult对象。
+        encoding: The encoding to use for decoding bytes. Defaults to 'utf-8'.
+                 用于解码字节的编码。默认为'utf-8'。
+
+    Returns:
+        ParseResult: A named tuple with URL components: scheme, netloc, path,
+                    params, query, and fragment.
+                    包含URL组件的命名元组：scheme、netloc、path、
+                    params、query和fragment。
+    """
+    # If the URL is already parsed, return it as is
+    # 如果URL已经解析，则原样返回
     if isinstance(url, ParseResult):
         return url
+    # Otherwise, convert to unicode and parse
+    # 否则，转换为unicode并解析
     return urlparse(to_unicode(url, encoding))
 
 
 def escape_ajax(url):
     """
-    Return the crawleable url according to:
-    https://developers.google.com/webmasters/ajax-crawling/docs/getting-started
+    Convert AJAX URLs to crawlable URLs according to Google's specification.
+    根据Google的规范将AJAX URL转换为可爬取的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_='
+    This function implements Google's "AJAX crawling scheme" which allows
+    search engines to crawl AJAX-based pages. It converts fragment identifiers
+    that start with an exclamation mark (!) to query parameters with the
+    "_escaped_fragment_" key.
+    此函数实现了Google的"AJAX爬取方案"，该方案允许搜索引擎爬取基于AJAX的页面。
+    它将以感叹号(!)开头的片段标识符转换为带有"_escaped_fragment_"键的查询参数。
 
-    URLs that are not "AJAX crawlable" (according to Google) returned as-is:
+    See: https://developers.google.com/webmasters/ajax-crawling/docs/getting-started
 
-    >>> 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'
+    Args:
+        url: The URL to convert.
+             要转换的URL。
+
+    Returns:
+        str: The crawlable URL with _escaped_fragment_ parameter if the URL
+             contains an AJAX fragment, or the original URL otherwise.
+             如果URL包含AJAX片段，则返回带有_escaped_fragment_参数的可爬取URL，
+             否则返回原始URL。
+
+    Examples:
+        >>> 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'
     """
+    # Split the URL into the part before the fragment and the fragment itself
+    # 将URL拆分为片段之前的部分和片段本身
     defrag, frag = urldefrag(url)
+
+    # If the fragment doesn't start with '!', it's not an AJAX URL
+    # 如果片段不以'!'开头，则它不是AJAX URL
     if not frag.startswith('!'):
         return url
+
+    # Convert the AJAX URL to a crawlable URL by adding the _escaped_fragment_ parameter
+    # 通过添加_escaped_fragment_参数将AJAX URL转换为可爬取的URL
     return add_or_replace_parameter(defrag, '_escaped_fragment_', frag[1:])
 
 
 def add_http_if_no_scheme(url):
-    """Add http as the default scheme if it is missing from the url."""
+    """
+    Add http as the default scheme if it is missing from the URL.
+    如果URL中缺少协议，则添加http作为默认协议。
+
+    This function checks if the URL already has a scheme (like http://, https://, ftp://).
+    If not, it adds 'http:' or 'http://' depending on whether the URL already has a netloc.
+    此函数检查URL是否已有协议（如http://、https://、ftp://）。
+    如果没有，它会添加'http:'或'http://'，具体取决于URL是否已有网络位置。
+
+    Args:
+        url: The URL to check and possibly modify.
+             要检查并可能修改的URL。
+
+    Returns:
+        str: The URL with a scheme, either the original one or with 'http' added.
+             带有协议的URL，可能是原始协议或添加了'http'。
+
+    Examples:
+        >>> add_http_if_no_scheme("example.com")
+        'http://example.com'
+        >>> add_http_if_no_scheme("http://example.com")
+        'http://example.com'
+        >>> add_http_if_no_scheme("https://example.com")
+        'https://example.com'
+    """
+    # Check if the URL already has a scheme
+    # 检查URL是否已有协议
     match = re.match(r"^\w+://", url, flags=re.I)
     if not match:
+        # Parse the URL to determine if it has a netloc
+        # 解析URL以确定它是否有网络位置
         parts = urlparse(url)
+        # Add the appropriate http scheme
+        # 添加适当的http协议
         scheme = "http:" if parts.netloc else "http://"
         url = scheme + url
 
@@ -84,6 +262,24 @@ def add_http_if_no_scheme(url):
 
 
 def _is_posix_path(string):
+    """
+    Check if a string looks like a POSIX filesystem path.
+    检查字符串是否看起来像POSIX文件系统路径。
+
+    This function uses a regular expression to check if the string matches
+    common patterns for POSIX filesystem paths, such as absolute paths,
+    relative paths, and paths with home directory references.
+    此函数使用正则表达式检查字符串是否匹配POSIX文件系统路径的常见模式，
+    如绝对路径、相对路径和带有主目录引用的路径。
+
+    Args:
+        string: The string to check.
+               要检查的字符串。
+
+    Returns:
+        bool: True if the string looks like a POSIX path, False otherwise.
+              如果字符串看起来像POSIX路径，则为True，否则为False。
+    """
     return bool(
         re.match(
             r'''
@@ -106,13 +302,31 @@ def _is_posix_path(string):
 
 
 def _is_windows_path(string):
+    """
+    Check if a string looks like a Windows filesystem path.
+    检查字符串是否看起来像Windows文件系统路径。
+
+    This function uses a regular expression to check if the string matches
+    common patterns for Windows filesystem paths, such as drive letters (C:\)
+    or UNC paths (\\server\share).
+    此函数使用正则表达式检查字符串是否匹配Windows文件系统路径的常见模式，
+    如驱动器号（C:\）或UNC路径（\\server\share）。
+
+    Args:
+        string: The string to check.
+               要检查的字符串。
+
+    Returns:
+        bool: True if the string looks like a Windows path, False otherwise.
+              如果字符串看起来像Windows路径，则为True，否则为False。
+    """
     return bool(
         re.match(
             r'''
             ^
             (
-                [a-z]:\\
-                | \\\\
+                [a-z]:\\        # Drive letter followed by :\
+                | \\\\          # Or UNC path starting with \\
             )
             ''',
             string,
@@ -122,38 +336,129 @@ def _is_windows_path(string):
 
 
 def _is_filesystem_path(string):
+    """
+    Check if a string looks like a filesystem path (either POSIX or Windows).
+    检查字符串是否看起来像文件系统路径（POSIX或Windows）。
+
+    This function combines the checks for both POSIX and Windows paths.
+    此函数结合了对POSIX和Windows路径的检查。
+
+    Args:
+        string: The string to check.
+               要检查的字符串。
+
+    Returns:
+        bool: True if the string looks like a filesystem path, False otherwise.
+              如果字符串看起来像文件系统路径，则为True，否则为False。
+    """
     return _is_posix_path(string) or _is_windows_path(string)
 
 
 def guess_scheme(url):
-    """Add an URL scheme if missing: file:// for filepath-like input or
-    http:// otherwise."""
+    """
+    Add an appropriate URL scheme if missing from the input.
+    如果输入中缺少适当的URL协议，则添加它。
+
+    This function examines the input and adds an appropriate scheme:
+    - 'file://' for filesystem paths (both POSIX and Windows)
+    - 'http://' for other inputs that look like URLs
+    此函数检查输入并添加适当的协议：
+    - 对于文件系统路径（POSIX和Windows），添加'file://'
+    - 对于看起来像URL的其他输入，添加'http://'
+
+    Args:
+        url: The URL or path to process.
+             要处理的URL或路径。
+
+    Returns:
+        str: The URL with an appropriate scheme added if it was missing.
+             添加了适当协议（如果缺少）的URL。
+
+    Note:
+        This function uses any_to_uri() from w3lib.url to convert filesystem
+        paths to proper file:// URLs.
+        此函数使用w3lib.url中的any_to_uri()将文件系统路径转换为适当的file://URL。
+    """
+    # If it looks like a filesystem path, convert it to a file:// URL
+    # 如果它看起来像文件系统路径，将其转换为file://URL
     if _is_filesystem_path(url):
         return any_to_uri(url)
+    # Otherwise, add http:// if needed
+    # 否则，如果需要，添加http://
     return add_http_if_no_scheme(url)
 
 
 def strip_url(url, strip_credentials=True, strip_default_port=True, origin_only=False, strip_fragment=True):
+    """
+    Strip a URL string of some of its components.
+    从URL字符串中去除某些组件。
 
-    """Strip URL string from some of its components:
+    This function allows selectively removing parts of a URL, such as credentials,
+    default ports, paths, queries, and fragments. It's useful for normalizing URLs
+    or removing sensitive information.
+    此函数允许选择性地移除URL的部分内容，如凭据、默认端口、路径、查询和片段。
+    它对于规范化URL或移除敏感信息很有用。
 
-    - ``strip_credentials`` removes "user:password@"
-    - ``strip_default_port`` removes ":80" (resp. ":443", ":21")
-      from http:// (resp. https://, ftp://) URLs
-    - ``origin_only`` replaces path component with "/", also dropping
-      query and fragment components ; it also strips credentials
-    - ``strip_fragment`` drops any #fragment component
-    """
+    Args:
+        url: The URL to strip.
+             要处理的URL。
+        strip_credentials: Whether to remove "user:password@" from the URL.
+                          是否从URL中移除"user:password@"。
+                          Defaults to True.
+                          默认为True。
+        strip_default_port: Whether to remove default ports (":80" for http,
+                           ":443" for https, ":21" for ftp) from the URL.
+                           是否从URL中移除默认端口（http的":80"，
+                           https的":443"，ftp的":21"）。
+                           Defaults to True.
+                           默认为True。
+        origin_only: Whether to keep only the origin part of the URL (scheme and netloc),
+                    replacing the path with "/" and removing params, query, and fragment.
+                    是否只保留URL的源部分（协议和网络位置），
+                    将路径替换为"/"并移除参数、查询和片段。
+                    This also implies strip_credentials=True.
+                    这也意味着strip_credentials=True。
+                    Defaults to False.
+                    默认为False。
+        strip_fragment: Whether to remove any #fragment component from the URL.
+                       是否从URL中移除任何#片段组件。
+                       Defaults to True.
+                       默认为True。
+
+    Returns:
+        str: The stripped URL.
+             处理后的URL。
 
+    Examples:
+        >>> strip_url("http://user:pass@example.com:80/path?query#fragment")
+        'http://example.com/path?query'
+        >>> strip_url("http://user:pass@example.com:80/path?query#fragment",
+        ...           strip_credentials=False, strip_fragment=False)
+        'http://user:pass@example.com/path?query#fragment'
+        >>> strip_url("http://user:pass@example.com:80/path?query#fragment",
+        ...           origin_only=True)
+        'http://example.com/'
+    """
+    # Parse the URL into its components
+    # 将URL解析为其组件
     parsed_url = urlparse(url)
     netloc = parsed_url.netloc
+
+    # Remove credentials if requested or if origin_only is True
+    # 如果请求或如果origin_only为True，则移除凭据
     if (strip_credentials or origin_only) and (parsed_url.username or parsed_url.password):
         netloc = netloc.split('@')[-1]
+
+    # Remove default ports if requested
+    # 如果请求，则移除默认端口
     if strip_default_port and parsed_url.port:
         if (parsed_url.scheme, parsed_url.port) in (('http', 80),
                                                     ('https', 443),
                                                     ('ftp', 21)):
             netloc = netloc.replace(f':{parsed_url.port}', '')
+
+    # Reconstruct the URL with the desired components
+    # 使用所需组件重建URL
     return urlunparse((
         parsed_url.scheme,
         netloc,

aio_scrapy-2.1.3.dist-info/RECORD

@@ -1,133 +0,0 @@
-aioscrapy/VERSION,sha256=BuGd6tadzBa8VzzJ8ktotpkH9M_Ur7nXA3LMa0YqmGI,5
-aioscrapy/__init__.py,sha256=esJeH66Mz9WV7XbotvZEjNn49jc589YZ_L2DKoD0JvA,858
-aioscrapy/__main__.py,sha256=rvTdJ0cQwbi29aucPj3jJRpccx5SBzvRcV7qvxvX2NQ,80
-aioscrapy/cmdline.py,sha256=1qhNg2Edl-Obmf2re2K4V8pJG7ubGfZZCzcHdKtdE_s,5159
-aioscrapy/crawler.py,sha256=6-ptivIjIGKdojOlZqXV0hV3x1Gont81tOC5u5JqIME,10330
-aioscrapy/exceptions.py,sha256=k1daw1hV_aqsaIKKibdyqcNPyVn5oUb07wmB2DRxfjs,2111
-aioscrapy/link.py,sha256=fXMqsHvYEzsuYi-sNDcElS7jV6Lusq0tjPkPUGOlyZw,1867
-aioscrapy/logformatter.py,sha256=y3etd28ACbpTbcGprJ_cQ086gxQY3k_QX_yxYFoF1AU,3028
-aioscrapy/process.py,sha256=uFkj2wzaBu0Vs3pGFKdJ4R-0Gn7hROX6EU-B5zddnyQ,1603
-aioscrapy/serializer.py,sha256=eTMSMHQZJidJ3-LzjmfJd-pkkG29G3NnrtYUx-eKB8w,734
-aioscrapy/signalmanager.py,sha256=S_dTEa8Y75x8SSHEQem014o-OmxwvfwaMH9w34lCkTc,2402
-aioscrapy/signals.py,sha256=rXkPNS6c9rIv_TzKU3lqYGQc8UA3CbqSsHL9O1U6MTE,610
-aioscrapy/spiderloader.py,sha256=XJ-lUUtf9Xy7172VzlvPzLes-2ym3GRw7lAdJ7sankc,3426
-aioscrapy/statscollectors.py,sha256=L1ykz0zCqt7Qw85NyhWH8zfwVOtnQOWMI0065YP03CQ,2036
-aioscrapy/commands/__init__.py,sha256=hNPzpaYpnX3mxLjQgKM211xAuMgjhxMwjpDRCrvFVwI,4769
-aioscrapy/commands/crawl.py,sha256=fKrQEdR-YJuiXpDIX3R0QdhOgjDwDye7C6ilrj77C1A,1020
-aioscrapy/commands/genspider.py,sha256=381W8-pjbASGXvYjrrgYWorJD9BjURa25oolDm0QI1Q,5426
-aioscrapy/commands/list.py,sha256=j62GHgngGRdW-AGKCJBvrc_h26yj0JmEFBkXTvjRoi8,346
-aioscrapy/commands/runspider.py,sha256=albdJM3SUbWzhiOK1zsWklp3HqGSPRISTshg33EnZ_c,2067
-aioscrapy/commands/settings.py,sha256=sc0rwwfBQNySKX8uV3iJqv3i7SelFwNcrlHYxDupKOg,1798
-aioscrapy/commands/startproject.py,sha256=Rcc7JkN75Jp2t2aZIxBzPsWbLXChNAUSByDhcW_6Ig8,4001
-aioscrapy/commands/version.py,sha256=yqqTMlZkkiQhtbU9w_IqUWLMOAjqYlv24friEkPRQYM,485
-aioscrapy/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-aioscrapy/core/engine.py,sha256=h02-K2lQqlCxvNIlURgPpnhHCbyiJRIWrFJt5Ys7vZY,9843
-aioscrapy/core/scheduler.py,sha256=czCx5oHknXuHadpISTfoEMSKXXrlwJTmLTUQtHdtaTc,7407
-aioscrapy/core/scraper.py,sha256=eS_qEX_Q9fXZnK8Ou1wDtBJhRKk9JoUSnbn4c04u1cA,10750
-aioscrapy/core/downloader/__init__.py,sha256=2EUQHGS6Q8fy9eoDT_kmA-eYZEUBV9OkmTppfG05AFA,10039
-aioscrapy/core/downloader/handlers/__init__.py,sha256=CriaX2Cp4jUqzDDGZDB7HiIEgUWt2pnYVho6HMV6sJ0,3198
-aioscrapy/core/downloader/handlers/aiohttp.py,sha256=KY04ATlu2cTVF3Uxtvqpx1cGxOn2QVIGWoj7S3_UwF4,4266
-aioscrapy/core/downloader/handlers/curl_cffi.py,sha256=LpwWdHxctDOxVvhzYcgG1qGhPtw9DoqjUKEdrZlerAQ,2579
-aioscrapy/core/downloader/handlers/httpx.py,sha256=4XyLpiaXbO0AtPqctFJgYFX-5rJrKyf469YFpVJdcRY,3387
-aioscrapy/core/downloader/handlers/pyhttpx.py,sha256=phpWXtuvP-9tve3MDnWeto2Dmo25UTxgLYc12QEvMt4,2562
-aioscrapy/core/downloader/handlers/requests.py,sha256=UnV1WDyET8WMwyYYU0DcL_r420uz_0dK1ej5xAl2fwk,2317
-aioscrapy/core/downloader/handlers/playwright/__init__.py,sha256=PXS40Vv3KsV77QoyWCrWcHL6mItXxpTzwaCATB6RXiQ,4504
-aioscrapy/core/downloader/handlers/playwright/driverpool.py,sha256=qfIdGjORdn1MookO-ucIJ8NOeLrIQ0y0UJY_xuMzM_8,1374
-aioscrapy/core/downloader/handlers/playwright/webdriver.py,sha256=QFtAT--2Ea_Gg4x1EhMidyOwQjbqljUl4sKGB_hAA00,3530
-aioscrapy/db/__init__.py,sha256=ISBXM_-cCf5CgTLc3i_emLxV163-ZAbgttkQiRxokD0,2456
-aioscrapy/db/absmanager.py,sha256=6vlPcjDHOtZCHePiUYPe6ezRnM-TB4XLhmuw7APaWDk,1162
-aioscrapy/db/aiomongo.py,sha256=t4JpRPBBisF7_rz02Kp6AejrphLvLWg5rF-yYLIe2MI,3071
-aioscrapy/db/aiomysql.py,sha256=-xCLfeH7RzvghY1jqREAb_Qnz9q_dVjxoHGfz7sCqbU,3799
-aioscrapy/db/aiopg.py,sha256=WG4s_2X0b8LQHbZpoIrwZeuGHNolKj-SvmvAZQlCk00,3213
-aioscrapy/db/aiorabbitmq.py,sha256=tNKl4Kx7KM7H_lOj8xfeA0uD8PuBTVzySApTEn5TyAE,5583
-aioscrapy/db/aioredis.py,sha256=UOoTRTQUvghnq29bVL8v1HvksMXYOzHaS8Btgbpn0bY,2966
-aioscrapy/dupefilters/__init__.py,sha256=Dx_CN-wBYiatLj3cXbK0f5d66CTjzzTeex6565L1EsA,1765
-aioscrapy/dupefilters/disk.py,sha256=EMgxeC2a6aYCGKgp4QOs5xwHp33LUsOZ8pliKBTFx1c,1551
-aioscrapy/dupefilters/redis.py,sha256=YUUsnRQ326PjdM_FUWAWjgOWw92KwswAGnM-FmN8pv0,7559
-aioscrapy/http/__init__.py,sha256=yeQTT5W1iwr6dKznTS5d9vnx2hsB47i9roPM57wQp_0,597
-aioscrapy/http/headers.py,sha256=H-RJ6KqOsFFFAXORfvoyz3V-ud0I8TAj5Jt5fAACcLc,1573
-aioscrapy/http/request/__init__.py,sha256=PFoFU3ncTN-gj6Rx01rjVa_744Qfv3EH29mooW6JX9U,7121
-aioscrapy/http/request/form.py,sha256=pqexRCmGlTiE9FofKa3_OpoK6yoJlf9qk9hxNveDoaw,1382
-aioscrapy/http/request/json_request.py,sha256=qtWdF5UhuGy0QmyLKWm9Y86veISkZS5HyOJiavtEhP4,2051
-aioscrapy/http/response/__init__.py,sha256=6DyNQNVgpJ-Awd8Cu9eCTXF_nmQF87WoAPPj5aBrigA,6731
-aioscrapy/http/response/html.py,sha256=PiBguPg2uE1lY_WNjs419EqbZv38pGsZ5JqTUYQWeMU,303
-aioscrapy/http/response/playwright.py,sha256=0DX0L04hGv1zvtXvdYS7_UQFKbnbx2r7Sj-ZKirxtr0,1051
-aioscrapy/http/response/text.py,sha256=VxpjTIGtnVuUepa3GdsyX5kskqnFVCjmZmfonSynbhM,9844
-aioscrapy/http/response/xml.py,sha256=5iXsTuxFW1eBLrzYggjyf-FTDZwWZwY1ATZceIa5yxM,300
-aioscrapy/libs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-aioscrapy/libs/downloader/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-aioscrapy/libs/downloader/defaultheaders.py,sha256=tg_ULA0Y-41bZKG607mowFJQGVfnZ45LdR044DsjA_A,563
-aioscrapy/libs/downloader/downloadtimeout.py,sha256=hNh3OEj7rC0ceQrv_yrhR5lb5AvfxJ6cspj3qsQWj4o,704
-aioscrapy/libs/downloader/ja3fingerprint.py,sha256=DgTw74GXC_Bp94eD_bwoG6A_DphUHTt7bH4glBNXyV8,1058
-aioscrapy/libs/downloader/retry.py,sha256=0670bPz5lc4wUsWmYlhYdGZdeflsQdFhJbnwK1g0c84,4441
-aioscrapy/libs/downloader/stats.py,sha256=FlkS8Zm4j3SBjHb6caXwq08HvvZ37VKORGCAjlA2U38,1376
-aioscrapy/libs/downloader/useragent.py,sha256=E5x5dk9AxsSCGDDICJlTXwWXRkqAibWgesqG0VhAG8M,743
-aioscrapy/libs/extensions/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-aioscrapy/libs/extensions/closespider.py,sha256=LRv4G7RHwFeT9WeH6s0spO909BHvxdtlvHWLN-dlyno,2734
-aioscrapy/libs/extensions/corestats.py,sha256=WCZ4nnk6LUP7AdGx9mnuVm96iWMxHozxdNPr41r8HmQ,1820
-aioscrapy/libs/extensions/logstats.py,sha256=wSLbN9tmsw5I1FBxHjLfIdQo85fxJI7TmOefispaxc4,1844
-aioscrapy/libs/extensions/metric.py,sha256=cx9UnSdj6akzrPe_uwWHh_QKTNzD82VRrEjiiHOoAuc,5479
-aioscrapy/libs/extensions/throttle.py,sha256=yos2D3XZgH40G52kltMKv5_GeAK4MqpRwTu6FCErUh0,3512
-aioscrapy/libs/pipelines/__init__.py,sha256=XW5Ur6bhvGLo-w-tdUeIB4jkFpZxqUU9mbajfAAztb0,5642
-aioscrapy/libs/pipelines/csv.py,sha256=-PEZOt-3ndF0ePO7EnqjEqeCYMJR9wHv3XcpSq6QswI,2454
-aioscrapy/libs/pipelines/execl.py,sha256=a8sfgQCHUc0MIja9cPP4TZ6ghfkxYZuAzLDIK4_nQuo,6284
-aioscrapy/libs/pipelines/mongo.py,sha256=B3dhvspxc4lmPh2noqARYV-rFuHfivdSfZ7ZlPKnk7c,2323
-aioscrapy/libs/pipelines/mysql.py,sha256=gN4DnyuXTQvDvy9Gu-v8F6sT8l7GZEa45AD0d-Ckv8s,1022
-aioscrapy/libs/pipelines/pg.py,sha256=la-SflXtGFw4IQYlOn75Brw2IfmtOUcCh0gUSz_Jg-0,990
-aioscrapy/libs/spider/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-aioscrapy/libs/spider/depth.py,sha256=IZoLS-JAqLl79JrQQf5p8aubN4c82g44M2iUkhRhXjM,1938
-aioscrapy/libs/spider/httperror.py,sha256=v8_zuTpzyU7nszo-97TEE5iniKPdrvKrPKx6bKDtQyI,1857
-aioscrapy/libs/spider/offsite.py,sha256=QQx15cozRPsjIvYobeiIgTeMwgtgDk5yMgf6Y6qT9s4,2941
-aioscrapy/libs/spider/referer.py,sha256=vdbk_uQI4o0MncCHQauVX7xcxERWSqw5ZkaJVVrYcr0,13768
-aioscrapy/libs/spider/urllength.py,sha256=D2sEt-LeibHYfkO1tUJxENeyI1PrwIb7HrLIBNU3HdA,1151
-aioscrapy/middleware/__init__.py,sha256=Ej7BAmxdHDqaytQT1XA3V73CpBedkZBQsRni0fduuck,396
-aioscrapy/middleware/absmanager.py,sha256=dwm4nEyRIjP_V6BJqI-tl9NZF0HwsafDNeWyqZCwSrA,3410
-aioscrapy/middleware/downloader.py,sha256=SSeHXtECbGE5r6o6EXLo9ZIrPX6wqkFTwEoN4F6qHgM,3199
-aioscrapy/middleware/extension.py,sha256=LS6Q9VFYVa9oemS7DiKsyehhz8244alj4Jtlnl0f4DY,420
-aioscrapy/middleware/itempipeline.py,sha256=_Htfrs3vzIUfajTOzQLdGaX_4xTFtSSoFzyhZJMyZw8,674
-aioscrapy/middleware/spider.py,sha256=QvV5dchOlskBn1sXKd5dj6s9zSZmlT6LibydCjfmYjU,6361
-aioscrapy/proxy/__init__.py,sha256=Cwua97Z-ezxtDSlud7mCOAV-iExY7RX_8O1oP5PS__k,1807
-aioscrapy/proxy/redis.py,sha256=LFfnnkihf6Wq1-HeRzPLVEiy5e5wxJbMY7htU-C_Pd8,2711
-aioscrapy/queue/__init__.py,sha256=MKHNOgcZRAjFHAxoKLujvsBCkB_Ne1-gz5DqNbdTYNA,2037
-aioscrapy/queue/memory.py,sha256=_Dvkd-HXwdR8B-wsEPlHNWbAgaMH9M_UGZhF21LbnHA,3140
-aioscrapy/queue/rabbitmq.py,sha256=rE1GCoIGxoaV4KAi_9Umt623A00FaHHIFV5ZH_nypzY,2516
-aioscrapy/queue/redis.py,sha256=KU31ZNciLI9xxZDxsDhtOPLtmkxZQlRPOx_1z8afdwY,4788
-aioscrapy/scrapyd/__init__.py,sha256=Ey14RVLUP7typ2XqP8RWcUum2fuFyigdhuhBBiEheIo,68
-aioscrapy/scrapyd/runner.py,sha256=tewEkdNTMrBoredCbhmdrswSrF-GWsU3MLgC__ntnzQ,1777
-aioscrapy/settings/__init__.py,sha256=GuiVhezV8U2J1B-WJwSvxxeH_1YWYD_Wighr9owC4HU,15781
-aioscrapy/settings/default_settings.py,sha256=PrUOFYNnPIS8eCdqvRylMLBK-4tT-2MYuU6Nn8dQrx0,5639
-aioscrapy/spiders/__init__.py,sha256=oM_FzqWa46P6cjzarOO1cfDTQD2AuIPgaWZrmdMcuTI,4085
-aioscrapy/templates/project/aioscrapy.cfg,sha256=_nRHP5wtPnZaBi7wCmjWv5BgUu5NYFJZhvCTRVSipyM,112
-aioscrapy/templates/project/module/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-aioscrapy/templates/project/module/middlewares.py.tmpl,sha256=0eEf2LC0vYcWPH82HNqieYSORyUuIo3Bgl5t-neRAJ4,3469
-aioscrapy/templates/project/module/pipelines.py.tmpl,sha256=-MYA7MFAffH8FTG1VGAkhIJLQ6MOGMrWVDO7cI9jw9A,164
-aioscrapy/templates/project/module/settings.py.tmpl,sha256=AO2jmyokUhuhFqxMvsMihPgSY4ZrldsMs-BuOEVfvQY,1421
-aioscrapy/templates/project/module/spiders/__init__.py,sha256=Zg1uss1vaNjvld9s9Ccua50SxVZwpFTPwqpBHoCrWdU,164
-aioscrapy/templates/spiders/basic.tmpl,sha256=oO1vh7-TZLjvpwdrYC49TGe-A6Kulc8UIG4Sa0QhDfI,375
-aioscrapy/templates/spiders/single.tmpl,sha256=Ptmo_uFDGEffvpEMyxec7sxIyBbP05x0Grhn5u6lZbQ,1011
-aioscrapy/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-aioscrapy/utils/conf.py,sha256=NkSmKjOE7xVvrAWQu4ne3jOzNGucgZdWHPhGbpz8dPU,7208
-aioscrapy/utils/curl.py,sha256=I8eZWFNgvyUiJ2YS9-s3HltGNVG8XMMU0HPhlMxuxdA,3295
-aioscrapy/utils/decorators.py,sha256=gMQArNxF9QQc1bENA0IqDchAjqmfWvHGKOyUdjXdg6A,794
-aioscrapy/utils/deprecate.py,sha256=STy55Q8kZI8q8CQUfxK4QQVu1Rs4En3rlhzWc7p7T00,5467
-aioscrapy/utils/httpobj.py,sha256=ytec7IZzsQY_GwR___051hdbOWs1ZM6S57HwcNiu2es,708
-aioscrapy/utils/log.py,sha256=NRDivw8w21J77qEUeqqLdC4sgdIKaj2UAP6lDvWGotM,1697
-aioscrapy/utils/misc.py,sha256=9NOssEl7CP_c6R9skxyXwmz4bd-nZ_gkw6F0EybeLTQ,3509
-aioscrapy/utils/ossignal.py,sha256=jAsCIKu17KV45-9dZwEkFJHF31Y13KP_zxY0x49j1jo,896
-aioscrapy/utils/project.py,sha256=cT98HaR5JaNmm-Y1UzSuzXj6B5S7GlmMshUfMhjpjJY,2905
-aioscrapy/utils/python.py,sha256=38oD-OSjeGb3XZFJn3bt74PwGbejnBfLWC5-lkUL0g8,4462
-aioscrapy/utils/reqser.py,sha256=qjrYut6KtvGpLLd-HDM0cncNzWCtXgpH6NyERu_5A9g,487
-aioscrapy/utils/request.py,sha256=bkFaLDeebAOp7pF-7vta9LKOB2OR2s7V9jVKfA-XlqA,2418
-aioscrapy/utils/response.py,sha256=UPR1wTTAYZkLGiiIs28kJLhlF7WPrgLuW31l9LZuYKM,1341
-aioscrapy/utils/signal.py,sha256=bkqRgGMqQ82dly_D4tDe_0pHBbc9QUxBJqSsH9RSQf0,2282
-aioscrapy/utils/spider.py,sha256=Usq3UlCaDUvXGp0ojFt39UPKFrR2rbInlJc_q0Xk7Qc,610
-aioscrapy/utils/template.py,sha256=HR97X4lpv2WuqhuPfzTgaBN66fYnzHVpP6zQ5IoTwcI,833
-aioscrapy/utils/tools.py,sha256=WJowViZB8XEs2CFqjVvbqXK3H5Uvf4BgWgBD_RcHMaM,2319
-aioscrapy/utils/trackref.py,sha256=0nIpelT1d5WYxALl8SGA8vHNYsh-jS0Z2lwVEAhwx8E,2019
-aioscrapy/utils/url.py,sha256=8W8tAhU7lgfPOfzKp3ejJGEcLj1i_PnA_53Jv5LpxiY,5464
-aio_scrapy-2.1.3.dist-info/LICENSE,sha256=L-UoAEM3fQSjKA7FVWxQM7gwSCbeue6gZRAnpRS_UCo,1088
-aio_scrapy-2.1.3.dist-info/METADATA,sha256=ldFQ8PbukunEAMxkUNbPQsA2Iuo6VfyYwPQbjc7KETk,6506
-aio_scrapy-2.1.3.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-aio_scrapy-2.1.3.dist-info/entry_points.txt,sha256=WWhoVHZvqhW8a5uFg97K0EP_GjG3uuCIFLkyqDICgaw,56
-aio_scrapy-2.1.3.dist-info/top_level.txt,sha256=8l08KyMt22wfX_5BmhrGH0PgwZdzZIPq-hBUa1GNir4,10
-aio_scrapy-2.1.3.dist-info/RECORD,,