+DCf8E dZddlmZddlZddlZddlZddlZddlmZdZ dZ dZ ejd Z ejd jd d d ddZejdjdddZejd ejd ejd ejdejdejdejdejddZejdZejdZGddej(Zd%d&dZd'dZd(dZd)dZd*dZd+d Zd,d-d!Zd,d.d"Zd,d.d#Zd/d$Zy)0a An implementation of `urlparse` that provides URL validation and normalization as described by RFC3986. We rely on this implementation rather than the one in Python's stdlib, because: * It provides more complete URL validation. * It properly differentiates between an empty querystring and an absent querystring, to distinguish URLs with a trailing '?'. * It handles scheme, hostname, port, and path normalization. * It supports IDNA hostnames, normalizing them to their encoded form. * The API supports passing individual components, as well as the complete URL string. Previously we relied on the excellent `rfc3986` package to handle URL parsing and validation, but this module provides a simpler alternative, with less indirection required. ) annotationsN) InvalidURLizBABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-._~z !$&'()*+,;=z%[A-Fa-f0-9]{2}z(?:(?P{scheme}):)?(?://(?P{authority}))?(?P{path})(?:\?(?P{query}))?(?:#(?P{fragment}))?z([a-zA-Z][a-zA-Z0-9+.-]*)?z[^/?#]*z[^?#]*z[^#]*z.*scheme authoritypathqueryfragmentzA(?:(?P{userinfo})@)?(?P{host}):?(?P{port})?z(\[.*\]|[^:@]*))userinfohostportz[^@]*z(\[.*\]|[^:]*))rrr r r r r rz ^[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+$z^\[.*\]$ceZdZUded<ded<ded<ded<ded<ded <ded <edd Zedd Zdd ZddZy) ParseResultstrrr r int | Nonerr str | Noner r cdj|jr|jdndd|jvrd|jdn |j|jd|jgSdgS)N@:[])joinr r rselfs O/var/www/highfloat_scraper/venv/lib/python3.12/site-packages/httpx/_urlparse.pyrzParseResult.authorityiszww'+}}4==/#"$'499$4!DII;a $))#'99#8!DII;   ?A   cdjd|jvrd|jdn |j|jd|jgSdgS)Nrrrr)rr rrs rnetloczParseResult.netlocssdww$'499$4!DII;a $))#'99#8!DII;   ?A   rc |s|S|j|j|j|j|jd}|j |t di|S)Nrr)rrr r r updateurlparse)rkwargsdefaultss r copy_withzParseResult.copy_with|sRKkkIIZZ   'h''rc|j}dj|jr|jdnd|rd|nd|j|jd|jnd|j d|j gSdgS)Nrr//?#)rrrr r r )rrs r__str__zParseResult.__str__sNN ww%)[[4;;-q!b$-"YK 2 $(JJ$:!DJJ< '+}}'@!DMM?#    GI    rN)returnr)r%rr-r) __name__ __module__ __qualname____annotations__propertyrr r'r,rrrr`sX KM I  I       (  rrc t|tkDr tdtd|Dr tdd|vr%|d}t |t r t |n||d<d|vr0|jdxsd}|jd\|d<}|d<d |vsd |vrLt|jd dxsd}t|jd dxsd}|r|d|n||d <d |vr7|jd xsd}|jd \|d<}|d<|sd|d<d|vrD|jdxsd} d| vr+| jdr| jds d| d|d<|jD]q\} } |  t| tkDrtd| dtd| Drtd| dt| j| rdtd| dt j#|} | J| j%} |jd| dxsd}|jd| dxsd}|jd| dxsd}|jd| d}|jd| d}t&j#|}|J|j%}|jd |d xsd}|jd|dxsd} |jd|d}|j)}t|t*dz}t-| }t/||}|dk7}|dk7xs |dk7xs|du}t1||||r t3|}t|t*dz}|dnt|t*dz}|dnt|t*dz}t5|||||||S) Nz URL too longc3bK|]'}|jxr|j )ywNisascii isprintable.0chars r zurlparse..s* E4<<> 4$"2"2"44 4 E-/z,Invalid non-printable ASCII character in URLrr rrr usernamepasswordr raw_pathr*r r rrzURL component 'z ' too longc3bK|]'}|jxr|j )ywr6r7r:s rr=zurlparse..s*O4<<><$*:*:*<&<<Or>z8Invalid non-printable ASCII character in URL component ''zInvalid URL component 'rrr safe) has_scheme has_authorityz:/[]@z:/?[]@z:/?#[]@)lenMAX_URL_LENGTHrany isinstanceintrpop partitionquoteget startswithendswithitemsCOMPONENT_REGEX fullmatch URL_REGEXmatch groupdictAUTHORITY_REGEXlower SUB_DELIMS encode_hostnormalize_port validate_pathnormalize_pathr)urlr%rr _r?r@rA seperatorr keyvalue url_matchurl_dictrrr r r authority_matchauthority_dictr parsed_schemeparsed_userinfo parsed_host parsed_portrFrG parsed_path parsed_queryparsed_fragments rr$r$s+  3x. (( E EEGHH f~&0s&;Tv6H%+,2,<,VzV3J39r:J39r:9Az8*5xzV::j)/R5=5G5G5L2v 6'?"F7Ozz&!'R $; 4s9K a[F6N llnC U  5zN* ?3%z!BCCOOO NseSTU #3'11%8 #:3%q!ABBC"$I   ""$HZZ(8"4 5 ;F ;(=>D"I ::fhv. / 52D JJw 1 2Ezz*hz&:;H&++I6O  && &$..0Nzz*nZ&@AGRH ::fnV4 5 ;D ::fnV4 5D  M  S0@AO"4(K,T6:K"$J2M!2Mk6M$:]Kd#T W(<=K 5Z(5J#K  eH: ;Q&R  rcj|sytj|r tj||St j|r tj|dd|ddS|jrt|jtS tj|jjdS#tj$rt d|wxYw#tj$rt d|wxYw#tj$rt d|wxYw) NrzInvalid IPv4 address: rzInvalid IPv6 address: rDasciizInvalid IDNA hostname: )IPv4_STYLE_HOSTNAMErW ipaddress IPv4AddressAddressValueErrorrIPv6_STYLE_HOSTNAME IPv6Addressr8rOrZr[idnaencodedecode IDNAError)r s rr\r\s(   " "4 (  @  ! !$ '  " "4 ( @  ! !$q* -Abz  TZZ\ 33={{4::<(//88;** @5dX>? ? @** @5dX>? ? @ >>=24(;<<=s#CC+1D"C(+"D "D2c||dk(ry t|}ddddddj|}||k(ry|S#t$rtd|wxYw)NrzInvalid port: Pi)ftphttphttpswswss)rL ValueErrorrrP)rr port_as_int default_ports rr]r]Lsv |trz4$i rCr#NRRLl"  4>$2334s 4A c|r |r|jds tdyy|jdr td|jdr|s tdyy)z Path validation rules that depend on if the URL contains a scheme or authority component. See https://datatracker.ietf.org/doc/html/rfc3986.html#section-3.3 /z7For absolute URLs, path must be empty or begin with '/'r)zFURLs with no authority component cannot have a path starting with '//'rzBURLs with no scheme component cannot have a path starting with ':'N)rQr)r rFrGs rr^r^gsp ,VW W-4 ??4 X  ??3  T )3 rc|jd}g}|D]9}|dk(r |dk(r|s|dgk7s|j)|j|;dj|S)z Drop "." and ".." segments from a URL path. For example: normalize_path("/path/./to/somewhere/..") == "/path/to" r.z..r)splitrMappendr)r componentsoutput components rr_r_siCJF%    $ &RD. MM) $% 88F rcdj|jdDcgc]}d|d c}jScc}w)a  Replace a single character with the percent-encoded representation. Characters outside the ASCII range are represented with their a percent-encoded representation of their UTF-8 byte sequence. For example: percent_encode(" ") == "%20" rzutf-8%02x)rrzupper)r<bytes rpercent_encoders; 77t{{7/CDtaSzND E K K MMDs Ac6t|zdz}|D]}||vsyy)z< Determine if a given string is already quote-safe. rFT)UNRESERVED_CHARACTERSstringrENON_ESCAPED_CHARSr<s ris_safers6.4s: ( ( rct||r|St|z}dj|Dcgc]}||vr|n t|c}Scc}w)z1 Use percent-encoding to quote a string. rDr)rrrrrs rpercent_encodedrsRvD! -4 77QWX**t0D DX XsAcg}d}tjt|D]l}|j|j }}|j d}||k7r!|||}|j t|||j ||}n|t|k7r!||d} |j t| |dj|S)a Use percent-encoding to quote a string, omitting existing '%xx' escape sequences. See: https://www.rfc-editor.org/rfc/rfc3986#section-2.1 * `string`: The string to be percent-escaped. * `safe`: A string containing characters that may be treated as safe, and do not need to be escaped. Unreserved characters are always treated as safe. See: https://www.rfc-editor.org/rfc/rfc3986#section-2.3 rrDNr) refinditerPERCENT_ENCODED_REGEXstartendgrouprrrHr) rrEpartscurrent_positionrWstart_position end_position matched_text leading_text trailing_texts rrOrOs E2F; (',{{}eiik {{1~ - -!"2>BL LLDA B  \"' (3v;&/01  _]>? 775>rc dj|Dcgc]#\}}t|ddzt|dz%c}}Scc}}w)am We can use a much simpler version of the stdlib urlencode here because we don't need to handle a bunch of different typing cases, such as bytes vs str. https://github.com/python/cpython/blob/b2f7b2ef0b5421e01efb8c7bee2ef95d3bab77eb/Lib/urllib/parse.py#L926 Note that we use '%20' encoding for spaces. and '%2F for '/'. This is slightly different than `requests`, but is the behaviour that browsers use. See - https://github.com/encode/httpx/issues/2536 - https://github.com/encode/httpx/issues/2721 - https://docs.python.org/3/library/urllib.parse.html#urllib.parse.urlencode &rrD=)rr)rSkvs r urlencodersN 88 1 AB '# -0K K   s(A r")r`rr%rr-r)r rr-r)rzstr | int | Nonerrr-r)r rrFboolrGrr-None)r rr-r)r<rr-r)r)rrrErr-r)rrrErr-r)rSzlist[tuple[str, str]]r-r) __doc__ __future__rrtrtypingry _exceptionsrrIrr[compilerformatrVrYrTrsrw NamedTuplerr$r\r]r^r_rrrrOrr3rrrs"# #I " #45 BJJ *  f+     &"**T f     bjj56I& BJJx RZZ  4  7# BJJ) * BJJt  !bjj!DE bjj-4 &##4 nDN+=\66, N  Br