Zf+IdZddlmZddlZddlZddlZddlmZm Z ddl m Z ddl m Z ddlZddlZddlmZmZdd lmZmZmZdd lmZej2d Zej6j9d Zd Ze dGddZGddZ e Z!GddZ"e e!jF d ddZ$e e!jJdZ%GddZ&ddZ'y)aZ`tldextract` accurately separates a URL's subdomain, domain, and public suffix. It does this via the Public Suffix List (PSL). >>> import tldextract >>> tldextract.extract('http://forums.news.cnn.com/') ExtractResult(subdomain='forums.news', domain='cnn', suffix='com', is_private=False) >>> tldextract.extract('http://forums.bbc.co.uk/') # United Kingdom ExtractResult(subdomain='forums', domain='bbc', suffix='co.uk', is_private=False) >>> tldextract.extract('http://www.worldbank.org.kg/') # Kyrgyzstan ExtractResult(subdomain='www', domain='worldbank', suffix='org.kg', is_private=False) Note subdomain and suffix are _optional_. Not all URL-like inputs have a subdomain or a valid suffix. >>> tldextract.extract('google.com') ExtractResult(subdomain='', domain='google', suffix='com', is_private=False) >>> tldextract.extract('google.notavalidsuffix') ExtractResult(subdomain='google', domain='notavalidsuffix', suffix='', is_private=False) >>> tldextract.extract('http://127.0.0.1:8080/deployed/') ExtractResult(subdomain='', domain='127.0.0.1', suffix='', is_private=False) To rejoin the original hostname, if it was indeed a valid, registered hostname: >>> ext = tldextract.extract('http://forums.bbc.co.uk') >>> ext.registered_domain 'bbc.co.uk' >>> ext.fqdn 'forums.bbc.co.uk' ) annotationsN) CollectionSequence) dataclass)wraps) DiskCache get_cache_dir)lenient_netloc looks_like_iplooks_like_ipv6)get_suffix_lists tldextractTLDEXTRACT_CACHE_TIMEOUT)z4https://publicsuffix.org/list/public_suffix_list.datzQhttps://raw.githubusercontent.com/publicsuffix/list/master/public_suffix_list.datT)orderceZdZUdZded<ded<ded<ded<ed dZed d Zed d Zed d Z y ) ExtractResultzA URL's extracted subdomain, domain, and suffix. Also contains metadata, like a flag that indicates if the URL has a private suffix. str subdomaindomainsuffixbool is_privatecj|jr'|jr|jd|jSy)zJoins the domain and suffix fields with a dot, if they're both set. >>> extract('http://forums.bbc.co.uk').registered_domain 'bbc.co.uk' >>> extract('http://localhost:8080').registered_domain '' .)rrselfs 5lib/python3.12/site-packages/tldextract/tldextract.pyregistered_domainzExtractResult.registered_domainLs- ;;4;;kk]!DKK=1 1c|jrQ|js |jr9djd|j|j|jfDSy)zReturns a Fully Qualified Domain Name, if there is a proper domain/suffix. >>> extract('http://forums.bbc.co.uk/path/to/file').fqdn 'forums.bbc.co.uk' >>> extract('http://localhost:8080').fqdn '' rc3&K|] }|s| ywN).0is r z%ExtractResult.fqdn..csW!UVAWsr)rrrjoinrrs rfqdnzExtractResult.fqdnYsB ;;DKK4??88W T[['QWW Wr!c|jr9|js-|js!t|jr |jSy)aReturns the ipv4 if that is what the presented domain/url is. >>> extract('http://127.0.0.1/path/to/file').ipv4 '127.0.0.1' >>> extract('http://127.0.0.1.1/path/to/file').ipv4 '' >>> extract('http://256.1.1.1').ipv4 '' r)rrrr rs ripv4zExtractResult.ipv4fs1 KK[[DNNdkk*;; r!cd}t|j|k\rX|jddk(rF|jddk(r4|js(|js|jdd}t |r|Sy)aReturns the ipv6 if that is what the presented domain/url is. >>> extract('http://[aBcD:ef01:2345:6789:aBcD:ef01:127.0.0.1]/path/to/file').ipv6 'aBcD:ef01:2345:6789:aBcD:ef01:127.0.0.1' >>> extract('http://[aBcD:ef01:2345:6789:aBcD:ef01:127.0.0.1.1]/path/to/file').ipv6 '' >>> extract('http://[aBcD:ef01:2345:6789:aBcD:ef01:256.0.0.1]').ipv6 '' r[]rr)lenrrrr )rmin_num_ipv6_chars debracketeds ripv6zExtractResult.ipv6ysj   2 2 A#% B3&[[DNN++a+K{+""r!N)returnr) __name__ __module__ __qualname____doc____annotations__propertyr r*r,r5r%r!rrr@sl N K K     $r!rceZdZdZeedddef ddZ d ddZ d ddZ d dd Z d dd Z d dd Z e ddd Z d dd Zy) TLDExtractzOA callable for extracting, subdomain, domain, and suffix components from a URL.TFr%c$|xsd}td|D|_||_|js|s|js td||_||_d|_t|tr t|n||_ t||_ y)aConstruct a callable for extracting subdomain, domain, and suffix components from a URL. Upon calling it, it first checks for a JSON in `cache_dir`. By default, the `cache_dir` will live in the tldextract directory. You can disable the caching functionality of this module by setting `cache_dir` to `None`. If the cached version does not exist (such as on the first run), HTTP request the URLs in `suffix_list_urls` in order, until one returns public suffix list data. To disable HTTP requests, set this to an empty sequence. The default list of URLs point to the latest version of the Mozilla Public Suffix List and its mirror, but any similar document could be specified. Local files can be specified by using the `file://` protocol. (See `urllib2` documentation.) If there is no cached version loaded and no data is found from the `suffix_list_urls`, the module will fall back to the included TLD set snapshot. If you do not want this behavior, you may set `fallback_to_snapshot` to False, and an exception will be raised instead. The Public Suffix List includes a list of "private domains" as TLDs, such as blogspot.com. These do not fit `tldextract`'s definition of a suffix, so these domains are excluded by default. If you'd like them included instead, set `include_psl_private_domains` to True. You can pass additional suffixes in `extra_suffixes` argument without changing list URL cache_fetch_timeout is passed unmodified to the underlying request object per the requests documentation here: http://docs.python-requests.org/en/master/user/advanced/#timeouts cache_fetch_timeout can also be set to a single value with the environment variable TLDEXTRACT_CACHE_TIMEOUT, like so: TLDEXTRACT_CACHE_TIMEOUT="1.2" When set this way, the same timeout value will be used for both connect and read timeouts r%c3^K|]%}|js|j'ywr$)strip)r&urls rr(z&TLDExtract.__init__..s#& syy{CIIK& s--zThe arguments you have provided disable all ways for tldextract to obtain data. Please provide a suffix list data, a cache_dir, or set `fallback_to_snapshot` to `True`.N) tuplesuffix_list_urlsfallback_to_snapshot ValueErrorinclude_psl_private_domainsextra_suffixes _extractor isinstancerfloatcache_fetch_timeoutr _cache)r cache_dirrDrErGrHrLs r__init__zTLDExtract.__init__s^,1r %& #3& ! %9!%%d6O6O;  ,G(,@D-s3 % &$   * r!Nc*|j|||S)zAlias for `extract_str`.session) extract_strrrBrGrRs r__call__zTLDExtract.__call__s%@'RRr!c<|jt|||S)aTake a string URL and splits it into its subdomain, domain, and suffix components. I.e. its effective TLD, gTLD, ccTLD, etc. components. >>> extractor = TLDExtract() >>> extractor.extract_str('http://forums.news.cnn.com/') ExtractResult(subdomain='forums.news', domain='cnn', suffix='com', is_private=False) >>> extractor.extract_str('http://forums.bbc.co.uk/') ExtractResult(subdomain='forums', domain='bbc', suffix='co.uk', is_private=False) Allows configuring the HTTP request via the optional `session` parameter. For example, if you need to use a HTTP proxy. See also `requests.Session`. >>> import requests >>> session = requests.Session() >>> # customize your session here >>> with session: ... extractor.extract_str("http://forums.news.cnn.com/", session=session) ExtractResult(subdomain='forums.news', domain='cnn', suffix='com', is_private=False) rQ)_extract_netlocr rTs rrSzTLDExtract.extract_strs)6## 3 !|j|j||S)aTake the output of urllib.parse URL parsing methods and further splits the parsed URL. Splits the parsed URL into its subdomain, domain, and suffix components, i.e. its effective TLD, gTLD, ccTLD, etc. components. This method is like `extract_str` but faster, as the string's domain name has already been parsed. >>> extractor = TLDExtract() >>> extractor.extract_urllib(urllib.parse.urlsplit('http://forums.news.cnn.com/')) ExtractResult(subdomain='forums.news', domain='cnn', suffix='com', is_private=False) >>> extractor.extract_urllib(urllib.parse.urlsplit('http://forums.bbc.co.uk/')) ExtractResult(subdomain='forums', domain='bbc', suffix='co.uk', is_private=False) rQ)rWnetlocrTs rextract_urllibzTLDExtract.extract_urllibs((## JJ3W$  r!cj|jddjddjdd}d}t||k\r-|ddk(r%|dd k(rt|d drtd |d d S|j d}|j |j ||\}}d} |t|cxk(r| k(rnnt|rtd |d |S|t|k7rdj||dnd } |dk\rdj|d|d z nd } |r||d z nd } t| | | |S)Nu。ru．u｡r.rr/r0r1rrF)rrQ)rG) replacer2r rsplit_get_tld_extractor suffix_indexr r)) rrYrGrRnetloc_with_ascii_dotsr3labelsr`rnum_ipv4_labelsrrrs rrWzTLDExtract._extract_netlocsc NN8X . WXx ( WXx (   & '+= =&q)S0&r*c15a;<$R)?PUVV'--c2#'#:#:$;$ ,v;V, W ! j 3v; 9/ 9m "? !%;RL L4@CK4O&/0UWr>sY !.*A%),1(*2?E+E+(E+# E+ &* E+ & E+0E+ E+T48+/ S S&1S) S  S48+/   &1 )    D48+/  @ &1 )    8,0 $D$D&1$D) $D  $DNKO550G5 5EE26!.! &!r!r>cXeZdZdZ d ddZe d d dZd d dZy) Triez:Trie for storing eTLDs with their labels in reverse-order.Nc6|r|ni|_||_||_y)zTODO.N)matchesendr)rrrrs rrOz Trie.__init__}s#*wr $r!ct}|D]}|j||g}|D]}|j|d|S)z?Create a Trie from a list of suffixes and return its root node.T)r} add_suffix)public_suffixesprivate_suffixes root_noders rcreatez Trie.creates] F % )F   ( )  #! & /F   . /r!c|}|jd}|j|D]6}||jvrt|j|<|j|}8d|_||_y)z+Append a suffix's labels to this Trie node.rTN)r^reverserr}rr)rrrnoderblabels rrzTrie.add_suffixshc" 'EDLL(&*f U#<<&D ' $r!)NFF)rzdict[str, Trie] | Nonerrrrr6rtr$)rzCollection[str]rzCollection[str] | Noner6r}F)rrrrr6rt)r7r8r9r:rO staticmethodrrr%r!rr}r}zssD+/ %' % % %  %48(0 $ %r!r}ct|||S)N)rGrR) TLD_EXTRACTOR)rBrGrRs rextractrs  )Dg r!c,tj|i|Sr$)rrg)argskwargss rrgrgs    0 00r!cJeZdZdZ d ddZdd dZ d d dZy) rrz8Wrapper around this project's main algo for PSL lookups.c$||_||_||_t||z|z|_t||z|_t j|j t||_t j|j |_ yr$) rGrnro frozensettlds_incl_privatetlds_excl_privater}rtlds_incl_private_trietlds_excl_private_trie)rrnrorprGs rrOz&_PublicSuffixListTLDExtractor.__init__s,G(&(!*;+E +R!S!*;+C!D&*kk  " "Il$;' #'+kk$2H2H&I#r!NcR| |j}|r |jS|jS)z,Get the currently filtered list of suffixes.)rGrr)rrGs rrjz"_PublicSuffixListTLDExtractor.tldss9 & .*.*J*J '+  " " '' r!c| |j}|r |jn |j}t|}|}t |D]}t |}||j vr#|dz}|j |}|jr|}?d|j v}|rPd|z|j v} | r||j djfcS|dz |j djfcSn||jfS)zReturn the index of the first suffix label, and whether it is private. Returns len(spl) if no suffix is found. r*!) rGrrr2reversed_decode_punycoderrr) rsplrGrr'jr decoded_label is_wildcardis_wildcard_exceptions rr`z*_PublicSuffixListTLDExtractor.suffix_indexs ' .*.*J*J '+  ' ',, H c] E,U3M ,Q||M288A-K(+m(;t||(K%(dll3/::::1udll3/:::: ! $$//!!r!r)rnryroryrpryrGrr$)rGrvr6zfrozenset[str])rryrGrvr6ztuple[int, bool])r7r8r9r:rOrjr`r%r!rrrrrscB-2 JJ J J &* J$  JN#"#";F#" #"r!rrc|j}|jd}|r tj|S|S#tt f$rY|SwxYw)Nzxn--)lower startswithidnadecode UnicodeError IndexError)rloweredlooks_like_punys rrrsYkkmG((0O ;;w' ' Nj)   N s<AArxru)rrr6r)(r: __future__rloggingos urllib.parseurllibcollections.abcrr dataclassesr functoolsrrrequestsrlr r remoter r r suffix_listr getLoggerLOGenvirongetr{rzrr>rr}rUrrgrrrr%r!rrs""H# 0! +BB)g % 9:   MMM`ccL .%.%b}05'+ !,% }11C"C"Lr!