act12

luisagalva · Jan 27, 2018 · 61d607e · 61d607e
1 parent f597772
commit 61d607e
Show file tree

Hide file tree

Showing 27 changed files with 286 additions and 416 deletions.
diff --git a/.DS_Store b/.DS_Store
diff --git a/Chinook b/Chinook
diff --git a/bin/.DS_Store b/bin/.DS_Store
diff --git a/bin/db/Chinook.class b/bin/db/Chinook.class
diff --git a/bin/db/Customer.class b/bin/db/Customer.class
diff --git a/bin/db/CustomerAdmin.class b/bin/db/CustomerAdmin.class
diff --git a/bin/lib/jsoup-1.11.1.jar b/bin/lib/jsoup-1.11.1.jar
diff --git a/bin/lib/log4j-api-2.9.1.jar b/bin/lib/log4j-api-2.9.1.jar
diff --git a/bin/lib/log4j-core-2.9.1.jar b/bin/lib/log4j-core-2.9.1.jar
diff --git a/bin/log4j2.xml b/bin/log4j2.xml
@@ -4,17 +4,16 @@
 		<Console name="Console" target="SYSTEM_OUT">
 			<PatternLayout pattern="%d{HH:mm:ss.SSS} [%t] %-5level %logger{36} - %msg%n" />
 		</Console>
-		<File name="Logfile" fileName="logs/aadmin.log" immediateFlush="true"
+		<File name="Logfile" fileName="logs/crawler.log" immediateFlush="true"
 			append="true">
 			<PatternLayout
 				pattern="%d{yyy-MM-dd HH:mm:ss.SSS} [%t] %-5level %logger{36} - %msg%n" />
 		</File>
 	</Appenders>
 	<Loggers>
-		<Logger name="db.CustomerAdmin" level="info">
-
-		</Logger>
-		<Root level="error"><AppenderRef ref="Logfile" /></Root>
+
+
+		<Root level="info"><AppenderRef ref="Logfile" /></Root>
 	</Loggers>
 
 </Configuration>
diff --git a/bin/web/Crawler.class b/bin/web/Crawler.class
diff --git a/bin/web/MainCrawler.class b/bin/web/MainCrawler.class
diff --git a/database/Chinook.db b/database/Chinook.db
diff --git a/jsoup.org.txt b/jsoup.org.txt
@@ -0,0 +1,39 @@
+/cookbook/modifying-data/set-html
+//jhy.io/
+http://www.opensource.org/
+/news/release-1.11.2
+discussion
+/cookbook/input/parse-body-fragment
+/cookbook/modifying-data/set-text
+bugs
+download
+/cookbook
+/cookbook/input/load-document-from-file
+/apidocs/
+/cookbook/
+/cookbook/input/load-document-from-url
+/apidocs/org/jsoup/select/Elements.html#html--
+/news/
+/download
+/cookbook/introduction/
+//try.jsoup.org/~LGB7rk_atM2roavV0d-czMt3J_g
+/cookbook/modifying-data/set-attributes
+http://whatwg.org/html
+/colophon
+/cookbook/input/parse-document-from-string
+https://github.com/jhy/jsoup/blob/master/src/main/java/org/jsoup/examples/Wikipedia.java
+/bugs
+/cookbook/extracting-data/attributes-text-html
+/apidocs/index.html?org/jsoup/select/Elements.html
+/
+/cookbook/extracting-data/selector-syntax
+http://en.wikipedia.org/wiki/Main_Page
+/cookbook/extracting-data/dom-navigation
+/cookbook/extracting-data/working-with-urls
+license
+/cookbook/introduction/parsing-a-document
+/cookbook/cleaning-html/whitelist-sanitizer
+/discussion
+//try.jsoup.org/
+http://github.com/jhy/jsoup/
+/cookbook/extracting-data/example-list-links
diff --git a/logs/crawler.log b/logs/crawler.log
@@ -0,0 +1,14 @@
+2017-11-20 22:22:49.453 [main] INFO  web.Crawler - Starting to crawl.
+2017-11-20 22:22:51.521 [main] INFO  web.Crawler - Artículos encontrados: 45
+2017-11-20 22:22:51.521 [main] INFO  web.Crawler - Subcrawling //try.jsoup.org/~LGB7rk_atM2roavV0d-czMt3J_g
+2017-11-20 22:22:51.522 [main] WARN  web.Crawler - java.lang.IllegalArgumentException: Malformed URL: //try.jsoup.org/~LGB7rk_atM2roavV0d-czMt3J_g
+2017-11-20 22:22:51.522 [main] INFO  web.Crawler - Subcrawling //try.jsoup.org/
+2017-11-20 22:22:51.522 [main] WARN  web.Crawler - java.lang.IllegalArgumentException: Malformed URL: //try.jsoup.org/
+2017-11-21 13:09:28.489 [main] INFO  web.Crawler - Starting to crawl.
+2017-11-21 13:09:30.367 [main] INFO  web.Crawler - Artículos encontrados: 7
+2017-11-24 12:58:58.284 [main] INFO  web.Crawler - Starting to crawl.
+2017-11-24 12:59:02.903 [main] INFO  web.Crawler - Artículos encontrados: 45
+2017-11-24 12:59:02.903 [main] INFO  web.Crawler - Subcrawling //try.jsoup.org/~LGB7rk_atM2roavV0d-czMt3J_g
+2017-11-24 12:59:02.912 [main] WARN  web.Crawler - java.lang.IllegalArgumentException: Malformed URL: //try.jsoup.org/~LGB7rk_atM2roavV0d-czMt3J_g
+2017-11-24 12:59:02.912 [main] INFO  web.Crawler - Subcrawling //try.jsoup.org/
+2017-11-24 12:59:02.912 [main] WARN  web.Crawler - java.lang.IllegalArgumentException: Malformed URL: //try.jsoup.org/
diff --git a/src/.DS_Store b/src/.DS_Store
diff --git a/src/db/Chinook.java b/src/db/Chinook.java
diff --git a/src/db/Customer.java b/src/db/Customer.java