pyspider安装

CentOS Linux release 7.0.1406 (Core)

cd pyspider
# 安装依赖包并安装
pip install -r requirements.txt
python setup.py install

# 重启mysql
service mysqld restart

# mysql -u root
# 修改root密码
mysql> use msyql
mysql> update user set password=password('123456') where user='root';


# 创建数据库并授权
mysql> create database taskdb;
mysql> create database projectdb;
mysql> create database resultdb;
mysql> create user 'pyspider'@'%';
mysql> create user pyspider@'localhost' identified by 'pyspider-pass';
mysql> grant select,insert,update,references,delete,create,drop,alter,index,trigger,create view,show view,execute,alter routine,create routine,create temporary tables,lock tables,event on taskdb.* to 'pyspider'@'%';
mysql> grant select,insert,update,references,delete,create,drop,alter,index,trigger,create view,show view,execute,alter routine,create routine,create temporary tables,lock tables,event on projectdb.* to 'pyspider'@'%';
mysql> grant select,insert,update,references,delete,create,drop,alter,index,trigger,create view,show view,execute,alter routine,create routine,create temporary tables,lock tables,event on resultdb.* to 'pyspider'@'%';
mysql> flush privileges;

修改配置文件(为集群做准备)
vi /etc/my.cnf
bind-address = 0.0.0.0

# 重启数据库 
service mysqld restart

cd /root/training/redis-2.8.12
make
make test
make install

# 为集群做准备
cd /root/training/redis-3.2.8
cp redis.conf /etc/

vi /etc/redis.conf
bind 0.0.0.0 

# 启动 redis 
redis-server /etc/redis.conf &

下载：wget https://bbuseruploads.s3.amazonaws.com/fd96ed93-2b32-46a7-9d2b-ecbc0988516a/downloads/396e7977-71fd-4592-8723-495ca4cfa7cc/phantomjs-2.1.1-linux-x86_64.tar.bz2?Signature=guF7TAUW11qr9nZXcTBHu7dg1ds%3D&Expires=1488510600&AWSAccessKeyId=AKIAIVFPT2YJYYZY3H4A&versionId=null&response-content-disposition=attachment%3B%20filename%3D%22phantomjs-2.1.1-linux-x86_64.tar.bz2%22

{
  "taskdb": "mysql+taskdb://pyspider:pyspider-pass@localhost:3306/taskdb",
  "projectdb": "mysql+projectdb://pyspider:pyspider-pass@localhost:3306/projectdb",
  "resultdb": "mysql+resultdb://pyspider:pyspider-pass@localhost:3306/resultdb",
  "message_queue": "redis://localhost:6379/db",
  "webui": {
    "port":5555,
    "username": "pyspider",
    "password": "pyspider-pass",
    "need-auth": true
  }
}

# pyspider -c /pyspider/config.json 
[W 170516 17:45:05 __init__:54] redis DB must zero-based numeric index, using 0 instead
[I 170516 17:45:05 result_worker:49] result_worker starting...
[W 170516 17:45:06 __init__:54] redis DB must zero-based numeric index, using 0 instead
[W 170516 17:45:06 __init__:54] redis DB must zero-based numeric index, using 0 instead
[W 170516 17:45:06 __init__:54] redis DB must zero-based numeric index, using 0 instead
[W 170516 17:45:06 __init__:54] redis DB must zero-based numeric index, using 0 instead
[I 170516 17:45:06 processor:211] processor starting...
[W 170516 17:45:07 __init__:54] redis DB must zero-based numeric index, using 0 instead
[W 170516 17:45:07 __init__:54] redis DB must zero-based numeric index, using 0 instead
[I 170516 17:45:07 tornado_fetcher:638] fetcher starting...
[W 170516 17:45:07 __init__:54] redis DB must zero-based numeric index, using 0 instead
[W 170516 17:45:07 __init__:54] redis DB must zero-based numeric index, using 0 instead
[W 170516 17:45:07 __init__:54] redis DB must zero-based numeric index, using 0 instead
[I 170516 17:45:09 scheduler:782] scheduler.xmlrpc listening on 127.0.0.1:23333
[I 170516 17:45:09 scheduler:647] scheduler starting...
phantomjs fetcher running on port 25555
[I 170516 17:45:09 scheduler:586] in 5m: new:0,success:0,retry:0,failed:0
[W 170516 17:45:10 __init__:54] redis DB must zero-based numeric index, using 0 instead
[W 170516 17:45:10 __init__:54] redis DB must zero-based numeric index, using 0 instead
[W 170516 17:45:10 __init__:54] redis DB must zero-based numeric index, using 0 instead
[W 170516 17:45:10 __init__:54] redis DB must zero-based numeric index, using 0 instead
[W 170516 17:45:10 __init__:54] redis DB must zero-based numeric index, using 0 instead
[I 170516 17:45:10 app:76] webui running on 0.0.0.0:5555

cd /root/supervisor-3.3.1
python setup.py install
或
pip install supervisor

; Sample supervisor config file.
;
; For more information on the config file, please see:
; http://supervisord.org/configuration.html
;
; Notes:
;  - Shell expansion ("~" or "$HOME") is not supported.  Environment
;    variables can be expanded using this syntax: "%(ENV_HOME)s".
;  - Comments must have a leading space: "a=b ;comment" not "a=b;comment".

[unix_http_server]
file=/tmp/supervisor.sock   ; (the path to the socket file)
chmod=0700                 ; socket file mode (default 0700)
chown=root:root       ; socket file uid:gid owner
;username=user              ; (default is no username (open server))
;password=123               ; (default is no password (open server))

[inet_http_server]         ; inet (TCP) server disabled by default
port=127.0.0.1:9001        ; (ip_address:port specifier, *:port for all iface)
username=supervisor             ; (default is no username (open server))
password=123               ; (default is no password (open server))

[supervisord]
logfile=/tmp/supervisord.log ; (main log file;default $CWD/supervisord.log)
logfile_maxbytes=50MB        ; (max main logfile bytes b4 rotation;default 50MB)
logfile_backups=10           ; (num of main logfile rotation backups;default 10)
loglevel=info                ; (log level;default info; others: debug,warn,trace)
pidfile=/tmp/supervisord.pid ; (supervisord pidfile;default supervisord.pid)
nodaemon=false               ; (start in foreground if true;default false)
minfds=1024                  ; (min. avail startup file descriptors;default 1024)
minprocs=200                 ; (min. avail process descriptors;default 200)
;umask=022                   ; (process file creation umask;default 022)
;user=chrism                 ; (default is current user, required if root)
;identifier=supervisor       ; (supervisord identifier, default is 'supervisor')
;directory=/tmp              ; (default is not to cd during start)
;nocleanup=true              ; (don't clean up tempfiles at start;default false)
;childlogdir=/tmp            ; ('AUTO' child log dir, default $TEMP)
;environment=KEY="value"     ; (key value pairs to add to environment)
;strip_ansi=false            ; (strip ansi escape codes in logs; def. false)

; the below section must remain in the config file for RPC
; (supervisorctl/web interface) to work, additional interfaces may be
; added by defining them in separate rpcinterface: sections
[rpcinterface:supervisor]
supervisor.rpcinterface_factory = supervisor.rpcinterface:make_main_rpcinterface

[supervisorctl]
serverurl=unix:///tmp/supervisor.sock ; use a unix:// URL  for a unix socket
;serverurl=http://127.0.0.1:9001 ; use an http:// url to specify an inet socket
username=suppervisor             ; should be same as http_username if set
password=123                ; should be same as http_password if set
prompt=mysupervisor         ; cmd line prompt (default "supervisor")
history_file=~/.sc_history  ; use readline history if available

; The below sample program section shows all possible program subsection values,
; create one or more 'real' program: sections to be able to control them under
; supervisor.

;[program:theprogramname]
;command=/bin/cat              ; the program (relative uses PATH, can take args)
;process_name=%(program_name)s ; process_name expr (default %(program_name)s)
;numprocs=1                    ; number of processes copies to start (def 1)
;directory=/tmp                ; directory to cwd to before exec (def no cwd)
;umask=022                     ; umask for process (default None)
;priority=999                  ; the relative start priority (default 999)
;autostart=true                ; start at supervisord start (default: true)
;startsecs=1                   ; # of secs prog must stay up to be running (def. 1)
;startretries=3                ; max # of serial start failures when starting (default 3)
;autorestart=unexpected        ; when to restart if exited after running (def: unexpected)
;exitcodes=0,2                 ; 'expected' exit codes used with autorestart (default 0,2)
;stopsignal=QUIT               ; signal used to kill process (default TERM)
;stopwaitsecs=10               ; max num secs to wait b4 SIGKILL (default 10)
;stopasgroup=false             ; send stop signal to the UNIX process group (default false)
;killasgroup=false             ; SIGKILL the UNIX process group (def false)
;user=chrism                   ; setuid to this UNIX account to run the program
;redirect_stderr=true          ; redirect proc stderr to stdout (default false)
;stdout_logfile=/a/path        ; stdout log path, NONE for none; default AUTO
;stdout_logfile_maxbytes=1MB   ; max # logfile bytes b4 rotation (default 50MB)
;stdout_logfile_backups=10     ; # of stdout logfile backups (default 10)
;stdout_capture_maxbytes=1MB   ; number of bytes in 'capturemode' (default 0)
;stdout_events_enabled=false   ; emit events on stdout writes (default false)
;stderr_logfile=/a/path        ; stderr log path, NONE for none; default AUTO
;stderr_logfile_maxbytes=1MB   ; max # logfile bytes b4 rotation (default 50MB)
;stderr_logfile_backups=10     ; # of stderr logfile backups (default 10)
;stderr_capture_maxbytes=1MB   ; number of bytes in 'capturemode' (default 0)
;stderr_events_enabled=false   ; emit events on stderr writes (default false)
;environment=A="1",B="2"       ; process environment additions (def no adds)
;serverurl=AUTO                ; override serverurl computation (childutils)

; The below sample eventlistener section shows all possible
; eventlistener subsection values, create one or more 'real'
; eventlistener: sections to be able to handle event notifications
; sent by supervisor.

;[eventlistener:theeventlistenername]
;command=/bin/eventlistener    ; the program (relative uses PATH, can take args)
;process_name=%(program_name)s ; process_name expr (default %(program_name)s)
;numprocs=1                    ; number of processes copies to start (def 1)
;events=EVENT                  ; event notif. types to subscribe to (req'd)
;buffer_size=10                ; event buffer queue size (default 10)
;directory=/tmp                ; directory to cwd to before exec (def no cwd)
;umask=022                     ; umask for process (default None)
;priority=-1                   ; the relative start priority (default -1)
;autostart=true                ; start at supervisord start (default: true)
;startsecs=1                   ; # of secs prog must stay up to be running (def. 1)
;startretries=3                ; max # of serial start failures when starting (default 3)
;autorestart=unexpected        ; autorestart if exited after running (def: unexpected)
;exitcodes=0,2                 ; 'expected' exit codes used with autorestart (default 0,2)
;stopsignal=QUIT               ; signal used to kill process (default TERM)
;stopwaitsecs=10               ; max num secs to wait b4 SIGKILL (default 10)
;stopasgroup=false             ; send stop signal to the UNIX process group (default false)
;killasgroup=false             ; SIGKILL the UNIX process group (def false)
;user=chrism                   ; setuid to this UNIX account to run the program
;redirect_stderr=false         ; redirect_stderr=true is not allowed for eventlisteners
;stdout_logfile=/a/path        ; stdout log path, NONE for none; default AUTO
;stdout_logfile_maxbytes=1MB   ; max # logfile bytes b4 rotation (default 50MB)
;stdout_logfile_backups=10     ; # of stdout logfile backups (default 10)
;stdout_events_enabled=false   ; emit events on stdout writes (default false)
;stderr_logfile=/a/path        ; stderr log path, NONE for none; default AUTO
;stderr_logfile_maxbytes=1MB   ; max # logfile bytes b4 rotation (default 50MB)
;stderr_logfile_backups=10     ; # of stderr logfile backups (default 10)
;stderr_events_enabled=false   ; emit events on stderr writes (default false)
;environment=A="1",B="2"       ; process environment additions
;serverurl=AUTO                ; override serverurl computation (childutils)

; The below sample group section shows all possible group values,
; create one or more 'real' group: sections to create "heterogeneous"
; process groups.

;[group:thegroupname]
;programs=progname1,progname2  ; each refers to 'x' in [program:x] definitions
;priority=999                  ; the relative start priority (default 999)

; The [include] section can just contain the "files" setting.  This
; setting can list multiple files (separated by whitespace or
; newlines).  It can also contain wildcards.  The filenames are
; interpreted as relative to this file.  Included files *cannot*
; include files themselves.

;[include]
;files = relative/directory/*.ini
[group:pyspider]
programs=pyspider-fetcher,pyspider-processor

[program:pyspider-fetcher]
command=/python2.7/bin/pyspider -c /pyspider/config.json fetcher
autorestart=true
autostart=true
user=root
group=pyspider
stopasgroup=true

[program:pyspider-processor]
command=/python2.7/bin/pyspider -c /pyspider/config.json processor
autorestart=true
autostart=true
user=root
group=pyspider
stopasgroup=true
stderr_logfile=/var/Spider/Log/Process/spider_process_err.log
stdout_logfile=/var/Spider/Log/Process/spider_process_out.log