Created
October 10, 2010 16:28
-
-
Save uehaj/619366 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// g100pon #83 webスクレイピング(nekohtmlを内部で使っているHtmlUnit使用) | |
// HtmlUnit are using nekohtml under the hood. | |
@Grab('net.sourceforge.htmlunit:htmlunit:2.8') | |
import java.net.URL; | |
import com.gargoylesoftware.htmlunit.BrowserVersion; | |
import com.gargoylesoftware.htmlunit.WebClient; | |
proxyHost = null // set the proxy host name if you are in Firewall | |
proxyPort = 18080 | |
if (proxyHost != null) { | |
c = new WebClient(BrowserVersion.FIREFOX_3, proxyHost , proxyPort); | |
} | |
else { | |
c = new WebClient(BrowserVersion.FIREFOX_3); | |
} | |
c.setJavaScriptEnabled(false) | |
ins = new BufferedReader(new InputStreamReader(System.in)) | |
userid = null | |
password = null | |
if (System.console() != null) { | |
userid = System.console().readLine("Gmail Mail Address: ") | |
password = new String(System.console().readPassword("Password: ")) | |
} | |
else { | |
print "Gmail Mail Address: " | |
userid = ins.readLine() | |
print "Password: " | |
password = ins.readLine() | |
} | |
url = "https://mail.google.com/mail/?ui=mobile&zyp=c" | |
loginPage = c.getPage(new URL(url)); | |
loginPage.getElementById("Email").valueAttribute = userid | |
loginPage.getElementById("Passwd").valueAttribute = password | |
threadsPage = loginPage.getElementByName("signIn").click() | |
while (true) { | |
threads = threadsPage.getByXPath("//a[starts-with(@id,'subj')]") | |
threads.eachWithIndex { it,idx-> | |
println "[$idx]"+it.asText() | |
} | |
println "[p]rev [n]ext [q]uit" | |
print "> " | |
def cmd = ins.readLine() | |
switch (cmd) { | |
case ~/([0-9]+)/: | |
i = java.util.regex.Matcher.getLastMatcher().group(1) as int | |
thread = threads[i].click() | |
println thread.asText() | |
case ~/p/: | |
next = threadsPage.getByXPath("//a[@id='thn']") | |
if (next.size() != 0) { | |
threadsPage = next[0].click() | |
} | |
break; | |
case ~/n/: | |
prev = threadsPage.getByXPath("//a[@id='tho']") | |
if (prev.size() != 0) { | |
threadsPage = prev[0].click() | |
} | |
break; | |
case ~/q/: | |
System.exit(0); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment