{"id":102,"date":"2007-08-06T14:56:01","date_gmt":"2007-08-06T14:56:01","guid":{"rendered":"http:\/\/newblog.mix1009.net\/?p=102"},"modified":"2007-08-06T14:56:01","modified_gmt":"2007-08-06T14:56:01","slug":"xpath-xml-api","status":"publish","type":"post","link":"https:\/\/mix1009.net\/?p=102","title":{"rendered":"XPath & libxml2"},"content":{"rendered":"

XML\uc740 \uaf64 \uc624\ub798\uc804\ubd80\ud130 \uc0ac\uc6a9\ud588\uc9c0\ub9cc, \uc5ec\ub7ec\uac00\uc9c0 \ubcf5\uc7a1\ud55c \uc6a9\uc5b4\ub4e4\uc774 \ub098\uc624\uba74\uc11c \uc880 \uba40\uc5b4\uc84c\ub358 \ub290\ub08c\uc774\uc5c8\ub294\ub370, XPath\ub294 \uc815\ub9d0 \ud504\ub85c\uadf8\ub798\uba38\uc5d0\uac8c \uc720\uc6a9\ud55c \ud234\uc778\uac83 \uac19\ub124\uc694.<\/p>\n

XPath\ub294 XML \ubb38\uc11c\uc5d0\uc11c \uc27d\uac8c element\ub97c \ucc3e\ub294 API\ub85c \ucffc\ub9ac\ub97c \ubb38\uc790\uc5f4\ub85c \ub118\uae30\uba74 \uc870\uac74\uc5d0 \ub9de\ub294 element\ub098 element \ub9ac\uc2a4\ud2b8\ub97c \ubc18\ud658\ud558\uac8c \ub429\ub2c8\ub2e4. 1.0 \ubc84\uc804\uc774 \uc788\uace0 2.0 \ubc84\uc804\uc774 \ucd5c\uadfc\uc5d0 \ub098\uc654\uc2b5\ub2c8\ub2e4. \uc544\uc9c1\uae4c\uc9c0\ub294 \ub77c\uc774\ube0c\ub7ec\ub9ac\ub4e4\uc774 1.0 \uae30\ubc18\uc774 \ub300\ubd80\ubd84\uc785\ub2c8\ub2e4.<\/p>\n

\ucffc\ub9ac\ub294 \uc608\uc81c\ub85c \uc0b4\ud3b4\ubcf4\ub294\uac83\uc774 \ube60\ub978\ub4ef\ud558\ub124\uc694.<\/p>\n

“A\/B\/C” : A element \ubc11\uc5d0 B element \ubc11\uc5d0 C element\ub4e4\uc740 \ucc3e\uc744\ub54c
\n“\/A\/B\/C” : \uc704\uc640 \uac19\uc9c0\ub9cc A\uac00 \ucd5c\uc0c1\uc704 element.
\n“\/A\/B\/C[1]” : C element\uc911 \uccab\ubc88\uc9f8
\n“\/A\/B\/C[2]” : C element\uc911 \ub450\ubc88\uc9f8
\n“\/\/C” : \ubaa8\ub4e0 C element
\n“B\/\/C” : B \ud558\uc704\uc5d0 \uc788\ub294 C element
\n“A\/B\/*” : A element \ubc11\uc5d0 B element \ubc14\ub85c \ubc11\uc758 \ubaa8\ub4e0 element
\n“A\/B\/\/*” : A element \ubc11\uc5d0 B element \ubc11\uc758 \ubaa8\ub4e0 element (\ud558\uc704 element \ud3ec\ud568)
\n“\/\/*” : \ubb38\uc11c\uc758 \ubaa8\ub4e0 element<\/p>\n

libxml2\ub77c\ub294 C \ub77c\uc774\ube0c\ub7ec\ub9ac\uac00 \uc788\uc9c0\ub9cc python wrapper\ub97c \uc774\uc6a9\ud558\uc5ec python\uc5d0\uc11c \uc704\uc758 \ucffc\ub9ac\ub4e4\uc744 \ub3cc\ub824\ubd24\uc2b5\ub2c8\ub2e4. \ud14c\uc2a4\ud2b8\ud574\ubcf8 \uacb0\uacfc \/\ub85c \uc2dc\uc791\ud558\uc9c0 \uc54a\ub294 \ucffc\ub9ac\ub4e4\uc740 \uc81c\ub300\ub85c \ub3d9\uc791\ud558\uc9c0 \uc54a\ub354\uad70\uc694. (\uac80\uc0c9\ub418\ub294 \uacb0\uacfc\uac00 \uc5c6\uc74c) \uc774\ub7f0 \ucffc\ub9ac\ub4e4\uc740 \uc55e\uc5d0 \/\/\ub97c \ubd99\uc5ec\uc8fc\uba74 \uc81c\ub300\ub85c \ub3d9\uc791\ud569\ub2c8\ub2e4.<\/p>\n

\uc544\ub798\ub294 python \uc18c\uc2a4\uc785\ub2c8\ub2e4. \uc911\uac04\uc5d0 \uc608\uc81c XML\uc744 \ubcf4\uae30 \uc88b\uac8c(?) \ub4e4\uc5ec\uc4f0\uae30\ud588\ub1a8\uc9c0\ub9cc \ucd9c\ub825\ud560\ub54c \ud55c\uc904\ub85c \ubcfc\uc218 \uc788\ub3c4\ub85d xml\uc5d0\uc11c \uacf5\ubc31\uacfc newline\uc744 \uc81c\uac70\ud569\ub2c8\ub2e4.<\/p>\n

[CODE type=python]
\nimport libxml2<\/p>\n

def xpathElements(ctxt, query):
\n    if query[0] == ‘\/’:
\n        print “\\”%s\\”” % query
\n    else:
\n        print “\\”%s\\” -> \\”\/\/%s\\”” % (query, query)
\n        query = “\/\/” + query
\n    res = ctxt.xpathEval(query)
\n    for e in res:
\n        print ”    %s (%s)” % (e.name, e)<\/p>\n

xml = “””
\n<A>
\n    <B>
\n        <C id=’c1’\/>
\n        <C id=’c2′>
\n            <D\/>
\n        <\/C>
\n        <E>
\n            <F\/>
\n            <A>
\n                <B>
\n                    <C\/>
\n                <\/B>
\n            <\/A>
\n        <\/E>
\n    <\/B>
\n<\/A>”””<\/p>\n

xml = ”.join([l.strip() for l in xml.splitlines()])<\/p>\n

doc = libxml2.parseDoc(xml)<\/p>\n

ctxt = doc.xpathNewContext()<\/p>\n

xpathElements(ctxt, “A\/B\/C”)
\nxpathElements(ctxt, “\/A\/B\/C”)
\nxpathElements(ctxt, “\/A\/B\/C[1]”)
\nxpathElements(ctxt, “\/A\/B\/C[2]”)
\nxpathElements(ctxt, “\/A\/B\/C[3]”)
\nxpathElements(ctxt, “\/\/C”)
\nxpathElements(ctxt, “\/\/B\/\/C”)
\nxpathElements(ctxt, “A\/B\/*”)
\nxpathElements(ctxt, “A\/B\/\/*”)
\nxpathElements(ctxt, “\/\/*”)
\n[\/HTML][\/CODE]<\/p>\n

\ub2e4\uc74c\uc740 \uc2e4\ud589\uacb0\uacfc\uc785\ub2c8\ub2e4.<\/p>\n

“A\/B\/C” -> “\/\/A\/B\/C”<\/span>
\n    C (<C id=”c1″\/>)
\n    C (<C id=”c2″><D\/><\/C>)
\n    C (<C\/>)
\n“\/A\/B\/C”<\/span>
\n    C (<C id=”c1″\/>)
\n    C (<C id=”c2″><D\/><\/C>)
\n“\/A\/B\/C[1]”<\/span>
\n    C (<C id=”c1″\/>)
\n“\/A\/B\/C[2]”<\/span>
\n    C (<C id=”c2″><D\/><\/C>)
\n“\/A\/B\/C[3]”<\/span>
“\/\/C”<\/span>
\n    C (<C id=”c1″\/>)
\n    C (<C id=”c2″><D\/><\/C>)
\n    C (<C\/>)
\n“\/\/B\/\/C”<\/span>
\n    C (<C id=”c1″\/>)
\n    C (<C id=”c2″><D\/><\/C>)
\n    C (<C\/>)
\n“A\/B\/*” -> “\/\/A\/B\/*”<\/span>
\n    C (<C id=”c1″\/>)
\n    C (<C id=”c2″><D\/><\/C>)
\n    E (<E><F\/><A><B><C\/><\/B><\/A><\/E>)
\n    C (<C\/>)
\n“A\/B\/\/*” -> “\/\/A\/B\/\/*”<\/span>
\n    C (<C id=”c1″\/>)
\n    C (<C id=”c2″><D\/><\/C>)
\n    D (<D\/>)
\n    E (<E><F\/><A><B><C\/><\/B><\/A><\/E>)
\n    F (<F\/>)
\n    A (<A><B><C\/><\/B><\/A>)
\n    B (<B><C\/><\/B>)
\n    C (<C\/>)
\n“\/\/*”<\/span>
\n    A (<A><B><C id=”c1″\/><C id=”c2″><D\/><\/C><E><F\/><A><B><C\/><\/B><\/A><\/E><\/B><\/A>)
\n    B (<B><C id=”c1″\/><C id=”c2″><D\/><\/C><E><F\/><A><B><C\/><\/B><\/A><\/E><\/B>)
\n    C (<C id=”c1″\/>)
\n    C (<C id=”c2″><D\/><\/C>)
\n    D (<D\/>)
\n    E (<E><F\/><A><B><C\/><\/B><\/A><\/E>)
\n    F (<F\/>)
\n    A (<A><B><C\/><\/B><\/A>)
\n    B (<B><C\/><\/B>)
\n    C (<C\/>)\n<\/div>\n

<\/p>\n","protected":false},"excerpt":{"rendered":"

XML\uc740 \uaf64 \uc624\ub798\uc804\ubd80\ud130 \uc0ac\uc6a9\ud588\uc9c0\ub9cc, \uc5ec\ub7ec\uac00\uc9c0 \ubcf5\uc7a1\ud55c \uc6a9\uc5b4\ub4e4\uc774 \ub098\uc624\uba74\uc11c \uc880 \uba40\uc5b4\uc84c\ub358 \ub290\ub08c\uc774\uc5c8\ub294\ub370, XPath\ub294 \uc815\ub9d0 \ud504\ub85c\uadf8\ub798\uba38\uc5d0\uac8c \uc720\uc6a9\ud55c \ud234\uc778\uac83 \uac19\ub124\uc694. XPath\ub294 XML \ubb38\uc11c\uc5d0\uc11c \uc27d\uac8c element\ub97c \ucc3e\ub294 API\ub85c \ucffc\ub9ac\ub97c \ubb38\uc790\uc5f4\ub85c \ub118\uae30\uba74 \uc870\uac74\uc5d0 \ub9de\ub294 element\ub098 element \ub9ac\uc2a4\ud2b8\ub97c \ubc18\ud658\ud558\uac8c \ub429\ub2c8\ub2e4. 1.0 \ubc84\uc804\uc774 \uc788\uace0 2.0 \ubc84\uc804\uc774 \ucd5c\uadfc\uc5d0 \ub098\uc654\uc2b5\ub2c8\ub2e4. \uc544\uc9c1\uae4c\uc9c0\ub294 \ub77c\uc774\ube0c\ub7ec\ub9ac\ub4e4\uc774 1.0 \uae30\ubc18\uc774 \ub300\ubd80\ubd84\uc785\ub2c8\ub2e4. \ucffc\ub9ac\ub294 \uc608\uc81c\ub85c \uc0b4\ud3b4\ubcf4\ub294\uac83\uc774 \ube60\ub978\ub4ef\ud558\ub124\uc694. “A\/B\/C” : A element \ubc11\uc5d0 […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[19],"tags":[91,92,93],"_links":{"self":[{"href":"https:\/\/mix1009.net\/index.php?rest_route=\/wp\/v2\/posts\/102"}],"collection":[{"href":"https:\/\/mix1009.net\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mix1009.net\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mix1009.net\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/mix1009.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=102"}],"version-history":[{"count":0,"href":"https:\/\/mix1009.net\/index.php?rest_route=\/wp\/v2\/posts\/102\/revisions"}],"wp:attachment":[{"href":"https:\/\/mix1009.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=102"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mix1009.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=102"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mix1009.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=102"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}