!hfSrSSKJr SSKrSSKrSSKJr SSKJrJ r SSK J r J r J r Jr SSKJr SSKJr SS KJr SS KJr SS KJr SS KJr SS jr\(a SSKJr SSKJr \ \ \!\ 4r"SSjr#SSjr$SSjr%SSjr&SSjr'SSjr(SSjr)SSjr*SSjr+S S!Sjjr,g)"zW This module contains general purpose URL functions not found in the standard library. ) annotationsN) import_module) TYPE_CHECKINGUnion) ParseResult urldefragurlparse urlunparse)warn)__all__)add_or_replace_parameter) any_to_uri) parse_url)ScrapyDeprecationWarningc USSS/[Q7;aDUS:XaSOSn[R"SUSUSUS 3[5 [ [ S 5U5$[ e) N _unquotepath _safe_charsr attributefunctionzThe scrapy.utils.url. z is deprecated, use w3lib.url.z instead.z w3lib.url)_public_w3lib_objectswarningsr rgetattrrAttributeError)nameobj_types W/root/1688_scrapy/alibaba-scraper/venv/lib/python3.13/site-packages/scrapy/utils/url.py __getattr__rsj  {S=RSS"&-"7;Z #D68*4RSWRXXa b $ }[1488 )Iterable)Spiderc^[U5RR5mT(dgUVs/sHo"R5PM nn[U4SjU55$s snf)z:Return True if the url belongs to any of the given domainsFc3d># UH%nTU:H=(d TRSU35v M' g7f).Nendswith).0dhosts r )url_is_from_any_domain..1s,H1 6t}}qW56s-0) _parse_urlnetloclowerany)urldomainsr(r)s @rurl_is_from_any_domainr2+sO c? ! ! ' ' )D ")*'Qwwy'G* HH HH+sA!c H[XR/[US/5Q5$)z2Return True if the url belongs to the given spiderallowed_domains)r2rr)r0spiders rurl_is_from_spiderr64s( ! kk CGF,=rB C rct^[U5RR5m[U4SjU55$)z?Return True if the url ends with one of the extensions providedc3F># UHnTRU5v M g7fNr%)r'extlowercase_paths rr*(url_has_any_extension..>sBz~&&s++zs!)r,pathr.r/)r0 extensionsr;s @rurl_has_any_extensionr?;s,_))//1N BzB BBrc[S[SS9 [U5upURS5(dU$[ USUSS5$)a( 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' zKescape_ajax() is deprecated and will be removed in a future Scrapy version.) stacklevel!_escaped_fragment_N)r rr startswith_add_or_replace_parameter)r0defragfrags r escape_ajaxrJAsL, U  S>LF ??3   $V-A48 LLrc[R"SU[RS9nU(d$[U5nUR(aSOSnX0-nU$)z=Add http as the default scheme if it is missing from the url.z^\w+://flagszhttp:zhttp://)rematch IGNORECASEr r-)r0rOpartsschemes radd_http_if_no_schemerSbs= HHZBMM :E  !LLil Jrc\[[R"SU[RS95$)Na ^ # start with... ( \. # ...a single dot, ( \. | [^/\.]+ # optionally followed by )? # either a second dot or some characters | ~ # $HOME )? # optional match of ".", ".." or ".blabla" / # at least one "/" for a file path, . # and something after the "/" rL)boolrNrOVERBOSEstrings r_is_posix_pathrYms,    **  rc~[[R"SU[R[R-S95$)Nzg ^ ( [a-z]:\\ | \\\\ ) rL)rUrNrOrPrVrWs r_is_windows_pathr[s5    --"**,   rc<[U5=(d [U5$r9)rYr[rWs r_is_filesystem_pathr]s & ! =%5f%==rcN[U5(a [U5$[U5$)zSAdd an URL scheme if missing: file:// for filepath-like input or http:// otherwise.)r] _any_to_urirS)r0s r guess_schemer`s%33  %%rc6[U5nURnU(dU(a6UR(dUR(aUR S5SnU(aLUR (a;UR UR 4S;aURSUR 3S5n[UR UU(aSO URU(aSO URU(aSO URU(aS45$UR45$)a|Strip URL string from some of its components: - ``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 @))httpP)httpsi)ftp:/) r r-usernamepasswordsplitportrRreplacer r=paramsqueryfragment)r0strip_credentialsstrip_default_port origin_onlystrip_fragment parsed_urlr-s r strip_urlrys"#J   F[z22c"2&  OO     0  !JOO#4 5r:     CJOOB:#4#4B:#3#3 B    '1&9&9    r)rstr)r0UrlTr1 Iterable[str]returnrU)r0r{r5z type[Spider]r}rU)r0r{r>r|r}rU)r0rzr}rz)rXrzr}rU)TTFT) r0rzrtrUrurUrvrUrwrUr}rz)-__doc__ __future__rrNr importlibrtypingrr urllib.parserrr r r w3lib.urlr rr rGrr_rr,scrapy.exceptionsrrcollections.abcr scrapyr!rzbytesr{r2r6r?rJrSrYr[r]r`ryrrrs # #'EE6K/-6 ( S% $%IC MB,  >&## - --- -  -  -r