source: nutchez-0.1/bin/nutchez-func.sh @ 95

Last change on this file since 95 was 94, checked in by waue, 15 years ago

0.1-2 fix some bug

  • Property svn:executable set to *
File size: 7.6 KB
Line 
1#!/bin/bash
2# Author: WeiYu Chen <waue _at_ nchc org tw>
3# License: GPL
4# Description: Eazily use for Nutch
5# .
6
7
8#DIALOG='dialog --backtitle "     NutchEz Setup Menu           -- powered by NCHC "'
9DIALOG=dialog
10
11# set 1 to display more for debug,
12VERB=0
13
14init_nutchez () {
15  if ! [ -e ~/.nutchez ] ;then
16    # copy from /etc/nutch
17    mkdir ~/.nutchez
18    cp -rf /etc/nutch/conf ~/.nutchez/
19    mkdir ~/.nutchez/log
20    cp -rf /etc/nutch/sav ~/.nutchez/
21    chown -R $LOGNAME:$LOGNAME ~/.nutchez
22  fi
23 
24}
25
26echo_dialog_v () {
27  if [ $VERB -eq 1 ]; then
28    $DIALOG --msgbox "$1" 16 51
29  fi
30}
31
32test_file () {
33  if ! test -e "$1" ; then
34    echo_dialog_v "test_file: \n can not find $1"
35    echo "" >  $1
36  else
37     echo_dialog_v "test_file: \n Touch  $1 ! \n Its content is \n `cat $1`"
38  fi
39}
40
41check_if_root() {
42   if [ ! "$UID" -eq "0" ]; then
43     echo_dialog_v "Hi [$LOGNAME] !! "
44     echo_dialog_v "You need to run this script \"`basename $0`\" as root."
45     exit 1
46   fi
47}
48
49promote_tempfile () {
50  echo_dialog_v "7. chang tmp as txt"
51  rm ~/.nutchez/sav/n.*.txt
52  mv /tmp/n.urls.tmp ~/.nutchez/sav/n.urls.txt
53  mv /tmp/n.robot.tmp ~/.nutchez/sav/n.robot.txt
54  mv /tmp/n.crawler.tmp ~/.nutchez/sav/n.crawler.txt
55  mv /tmp/n.tomcat.tmp ~/.nutchez/sav/n.tomcat.txt
56}
57
58clean_tempfile () {
59  echo_dialog_v "7. delete tmp"
60  rm /tmp/n.*.tmp
61}
62
63setup_nutchez () {   
64  if ! [ -e ~/.nutchez/urls ] ; then
65    # make url list dir
66    mkdir ~/.nutchez/urls
67  fi
68
69  if  [ -e ~/.nutchez/urls/urls.txt ] ; then
70    rm ~/.nutchez/urls/urls.txt
71  fi
72
73  cp ~/.nutchez/sav/n.urls.txt ~/.nutchez/urls/urls.txt
74
75  if [ $NOCONTINUE -eq 1 ]; then
76    echo_dialog_v " delete the ~/.nutchez/search/*"
77    DATE=`date +%y%m%d%H%M%S`
78    mv ~/.nutchez/search ~/.nutchez/search-$DATE
79    $DIALOG --msgbox "上次搜尋的結果改放到 ~/.nutchez/search-$DATE " 0 0
80    rm -f /tmp/search
81#    rm -rf ~/.nutchez/search/*
82  fi
83
84  if [ -e ~/.nutchez/conf/nutch-site.xml ] ; then
85    # set nutch-site.xml
86    sed -i -e "4s/<value>[a-zA-Z0-9]*</<value>$ROBOT</" ~/.nutchez/conf/nutch-site.xml
87  fi
88
89}
90
91install_tomcat (){
92  if ! [ -e ~/.nutchez/tomcat ] ;then
93    # isntall tomcat to home
94    cp -rf /opt/nutch/tomcat ~/.nutchez/
95    chown -R $LOGNAME:$LOGNAME ~/.nutchez/tomcat/
96    # make search dir
97    if ! [ -e ~/.nutchez/search ] ;then
98      mkdir ~/.nutchez/search
99    fi
100  fi
101  # change explorer port
102  sed -i -e "67s/<Connector port=\"[0-9]*\"/<Connector port=\"$PORT\"/" ~/.nutchez/tomcat/conf/server.xml
103}
104
105
106show_urls (){
107  # show urls : ok =0 ,cancel = 1
108  echo_dialog_v "2. show_urls !"
109  test_file  ~/.nutchez/sav/n.urls.txt
110  echo_dialog_v "2.1 test_file ~/.nutchez/sav return : $?"
111  # dialog begin
112  dialog --title "請輸入你要抓取的網址(一行一個網址)" --editbox ~/.nutchez/sav/n.urls.txt 16 51 2>/tmp/n.urls.tmp
113  RET=$?
114  echo_dialog_v "2.1 cat url: `cat /tmp/n.urls.tmp`"
115  return $RET
116}
117
118setup_robot () {
119  test_file ~/.nutchez/sav/n.robot.txt
120  echo_dialog_v "3. setup_robot"
121  # dialog
122  dialog --title "設定機器人名稱" --nocancel --inputbox " 這個爬網機器人,你要將他取名為:\n\n (ps: 這個設定只是禮貌性宣告,並不會對結果造成影響) \n" 16 55 "`cat ~/.nutchez/sav/n.robot.txt`" 2>/tmp/n.robot.tmp
123  echo_dialog_v "3.1 cat robot : `cat /tmp/n.robot.tmp`"
124}
125
126setup_crawler () {
127  echo_dialog_v "4. setup_crawler"
128  test_file ~/.nutchez/sav/n.crawler.txt
129  dialog --title "設定抓取深度" --nocancel --inputbox " 對於每個網址,你需要NutchEz爬多深呢?\n\n (ps: 初次體驗建議將深度設為1來感受需要多久)  \n " 16 51 "`cat ~/.nutchez/sav/n.crawler.txt`" 2>/tmp/n.crawler.tmp
130  echo_dialog_v "4.1 cat robot : `cat /tmp/n.robot.tmp`"
131}
132
133setup_tomcat () {
134  echo_dialog_v "5. setup_tomcat"
135  test_file ~/.nutchez/sav/n.tomcat.txt
136  dialog --title "設定網頁伺服器" --nocancel --inputbox " 你希望NutchEz將網頁伺服器開在哪個port \n\n (ps: 請選擇一個沒用到的port以免造成衝突 \n 也請盡量不要設成80以免造成你誤以為是apache的混淆) \n " 16 51 "`cat ~/.nutchez/sav/n.tomcat.txt`" 2>/tmp/n.tomcat.tmp
137  echo_dialog_v "5.1 cat tomcat : `cat /tmp/n.tomcat.tmp`"
138}
139
140continue_previous () {
141  echo_dialog_v "6. setup_tomcat"
142$DIALOG --title "清除上次搜尋" --clear \
143        --yesno "你是否要清除上一次爬網所得的結果,\n否則將加入到URL列裡增加搜尋負擔 \n\n ps: 選no的話,會跑相當相當久,\n 請慎重考慮之\n" 16 51
144
145case $? in
146  0)
147    NOCONTINUE=1;;
148  1)
149    NOCONTINUE=0;;
150  255)
151    echo "ESC pressed.";;
152esac
153echo_dialog_v " 6continue = $CONTINUE"
154}
155
156final_confirm () {
157  echo_dialog_v "7. final_confirm : start =0 , back =1 "
158  tempfile=/tmp/n.finalcheck.tmp
159
160  echo " \n 1. 你所選擇要爬取的網址為 : \n " > $tempfile
161  cat /tmp/n.urls.tmp >> $tempfile
162  echo " \n\n 2. 對於這個爬網機器人,你取名為 : \n" >> $tempfile
163  cat /tmp/n.robot.tmp >> $tempfile
164  echo " \n\n 3. 爬網的深度,你設定為 : \n " >> $tempfile
165  cat /tmp/n.crawler.tmp >> $tempfile
166  echo " \n\n 4. NutchEz將會把你的搜尋結果呈現在這個Port : \n " >> $tempfile
167  cat /tmp/n.tomcat.tmp >> $tempfile
168  if [ $NOCONTINUE -eq 0 ];then
169    echo " \n\n 5. 是否要清除上一次的收尋結果 : \n " >> $tempfile
170    echo_dialog_v " 7continue = $CONTINUE"
171    echo "NO" >> $tempfile
172  elif [ $NOCONTINUE -eq 1 ];then
173    echo " \n\n 5. 是否要清除上一次的收尋結果繼續搜尋 : \n " >> $tempfile
174    echo_dialog_v " 7continue = $CONTINUE"
175    echo "YES" >> $tempfile
176  else
177    echo_dialog_v " 無資料可匯入 "
178  fi
179  MSG=`cat $tempfile`
180  echo_dialog_v "7.1 final message :\n $MSG"
181  #read READ
182  $DIALOG --title "請檢查你的選擇 ! \n\n 若所有的設定都是正確的,你可以按 \"ok\",\n 若你按了 \"reset\" 則會重頭開始設定, \n 若你選擇 \"exit\" 則會跳出NutchEz的設定選單 \n ps: reset 與 exit都不會把資料記成預設值,請放心使用 " --clear \
183        --extra-button --extra-label "reset" --ok-label "ok" --cancel-label "exit" \
184        --yesno "$MSG" 26 51
185  RET=$?
186  echo_dialog_v "final return = $RET"
187  return $RET
188}
189
190# define paramaters
191
192set_nutchez_p () {
193  ROBOT=`cat ~/.nutchez/sav/n.robot.txt`
194  URLS=`cat ~/.nutchez/sav/n.urls.txt`
195  DEPTH=`cat ~/.nutchez/sav/n.crawler.txt`
196  PORT=`cat ~/.nutchez/sav/n.tomcat.txt`
197}
198start_crawl () {
199
200  echo_dialog_v "7. start_crawl"
201  setup_nutchez
202  install_tomcat
203  echo_dialog_v "/opt/nutch/bin/nutch crawl ~/.nutchez/urls -dir ~/.nutchez/search -depth $DEPTH"
204  echo_dialog_v "nutch conf dir = $NUTCH_CONF_DIR"
205  /opt/nutch/bin/nutch crawl ~/.nutchez/urls -dir ~/.nutchez/search -depth $DEPTH -topN 5000 -threads 1000
206}
207
208start_tomcat () {
209  echo_dialog_v "8. start_tomcat "
210  echo_dialog_v "/opt/nutch/tomcat/bin/startup.sh"
211  if [ -e /tmp/search ];then
212    rm -rf /tmp/search
213  fi
214  ln -sf ~/.nutchez/search/ /tmp/
215
216  pid_tc=$(ps axw -eo pid,command |\
217  grep "catalina" | grep "java" |\
218  grep "start" | awk '{print $1}')
219  if [ -z "$pid_tc" ]; then
220      echo_dialog_v "no another tomcat is running"
221  else
222      echo_dialog_v "tomcat had been started and the pid is $pid_tc"
223      echo_dialog_v "stop it first"
224      kill -9 $pid_tc
225      if [ -z $? ];then
226    echo_dialog_v " tomcat ($pid_tc) is  killed ..."
227      else
228    echo_dialog_v "kill error ..." 
229      fi
230  fi
231  echo "Starting Tomcat ...."
232  ~/.nutchez/tomcat/bin/startup.sh
233  sleep 3
234}
235
236show_report () {
237  echo_dialog_v "9. show_report "
238  FIREFOX=`which firefox`
239  RET=$?
240  if [ $RET -eq 0 ];then 
241    $FIREFOX -D 0.0 http://localhost:$PORT
242    RET=$?
243  fi
244  if ! [ $RET -eq 0 ];then
245    $DIALOG --msgbox "恭喜你已經完成了! \n 你可以用瀏覽器瀏覽: \n  http://host_ip:$PORT" 0 0 
246  fi
247}
Note: See TracBrowser for help on using the repository browser.