首页 > 建站知识

怎么用Python脚本挖掘几十万关键词

2018-11-20 13:49:00 海静

  在运转脚本之前,请肯定你是否安装了MySQLdb库,安装方式不妨去百度一下。

  #!/usr/local/bin/python

  #coding:utf8

  # 2015-6-26 DaoXin

  import pycurl, json, MySQLdb

  import StringIO

  import urllib, urllib2

  from random import choice

  import sys

  reload(sys)

  sys.setdefaultencoding('utf8')

网站优化

  #useragent 列表,众人不妨自行去采集。

  AGENTS = [

  "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.81 Safari/537.36",

  "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.27 (KHTML, like Gecko) Chrome/12.0.712.0 Safari/534.27",

  "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.24 Safari/535.1",

  "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.120 Safari/535.2",

  "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.36 Safari/535.7",

  "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:2.0b4pre) Gecko/20100815 Minefield/4.0b4pre",

  "Mozilla/5.0 (Windows; U; Windows NT 6.1; zh-CN) AppleWebKit/533.19.4 (KHTML, like Gecko) Version/5.0.2 Safari/533.18.5",

  "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-GB; rv:1.9.1.17) Gecko/20110123 (like Firefox/3.x) SeaMonkey/2.0.12",

  "Mozilla/5.0 (Windows NT 5.2; rv:10.0.1) Gecko/20100101 Firefox/10.0.1 SeaMonkey/2.7.1",

  "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; zh-CN) AppleWebKit/532.8 (KHTML, like Gecko) Chrome/4.0.302.2 Safari/532.8",

  "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_4; zh-CN) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.464.0 Safari/534.3",

  "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_5; zh-CN) AppleWebKit/534.13 (KHTML, like Gecko) Chrome/9.0.597.15 Safari/534.13",

  "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_2) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.186 Safari/535.1",

  "Mozilla/5.0 (Macintosh; U; PPC Mac OS X; en) AppleWebKit/125.2 (KHTML, like Gecko) Safari/125.8",

  "Mozilla/5.0 (Macintosh; U; PPC Mac OS X; fr-fr) AppleWebKit/312.5 (KHTML, like Gecko) Safari/312.3",

  "Mozilla/5.0 (Macintosh; U; PPC Mac OS X; en) AppleWebKit/418.8 (KHTML, like Gecko) Safari/419.3",

  "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1 Camino/2.2.1",

  "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0b6pre) Gecko/20100907 Firefox/4.0b6pre Camino/2.2a1pre",

  "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",

  "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_2) AppleWebKit/537.4 (KHTML like Gecko) Chrome/22.0.1229.79 Safari/537.4",

  "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_2; rv:10.0.1) Gecko/20100101 Firefox/10.0.1",

  "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:16.0) Gecko/20120813 Firefox/16.0",

  "Mozilla/5.0 (Macintosh; U; Intel Mac OS X; zh-CN) AppleWebKit/528.16 (KHTML, like Gecko, Safari/528.16) OmniWeb/v622.8.0.112941",

  "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_6; zh-CN) AppleWebKit/528.16 (KHTML, like Gecko, Safari/528.16) OmniWeb/v622.8.0",

  ]

  UserAgent = choice(AGENTS)

网站优化

  假如需求把挖走出的主要词保存到数据库,需求配置数据库关联信息

  class ConnDb():

  global host, user, passwd, db

  host = '111.111.111.111' #数据库IP

  user = 'python' #数据库用户名

  passwd = 'python' #数据库暗码

  db = 'testdb' # 数据库名

  def connDb(self):

  global cur

  conn = MySQLdb.connect(host=host, user=user, passwd=passwd, db=db, port=3306, charset = 'utf8')

  cur = conn.cursor()

  return cur

  # 这个curl方式是从@zero那里扒过来的。http://www.seoqx.com/post/341

  def curl(url, debug=False, **kwargs):

  while 1:

  try:

  s = StringIO.StringIO()

  c = pycurl.Curl()

  c.setopt(pycurl.URL, url)

  c.setopt(pycurl.REFERER, url)

  c.setopt(pycurl.FOLLOWLOCATION, True)

  c.setopt(pycurl.TIMEOUT, 60)

  c.setopt(pycurl.ENCODING, 'gzip')

  c.setopt(pycurl.USERAGENT, UserAgent)

  c.setopt(pycurl.NOSIGNAL, True)

  c.setopt(pycurl.WRITEFUNCTION, s.write)

  for k, v in kwargs.iteritems():

  c.setopt(vars(pycurl)[k], v)

  c.perform()

  c.close()

  return s.getvalue()

  except:

  if debug:

  raise

  continue

  command = int(raw_input("请选择导出模式;1:导出为txt,2:导入道数据库: "))

  if command == 1:

  FileWrite = open("output.txt", 'w')

  for line in open('sourceword.txt'):

  kw = str(line)

  jsons = curl('http://honeyimg.bdimg.com/recomword/recomWordCache_findRecomWord.htm?area_id=&word=' + urllib.quote_plus(kw))

  d = json.loads(jsons)

  try:

  dlist = d['data']['list']

  for item in dlist:

  indexs = item['total']

  keywords = item['word'].encode('utf-8')

  outstr = str(indexs) + ',' + str(keywords) + '\n'

  FileWrite.write(outstr)

  except TypeError, e:

  print 'TypeError, Pass', e

  continue

  print 'done to txt'

  elif command == 2:

  conndb = ConnDb()

  conndb.connDb()

  for line in open('sourceword.txt'):

  kw = str(line)

  jsons = curl('http://honeyimg.bdimg.com/recomword/recomWordCache_findRecomWord.htm?area_id=&word=' + urllib.quote_plus(kw))

  d = json.loads(jsons)

  try:

  dlist = d['data']['list']

  for item in dlist:

  indexs = item['total']

  #keywords = unicode(item['word'], 'utf-8')

  keywords = item['word'].encode("utf-8")

  sql = "insert into shangqing_keyword (id, total, keyword) values (null, '%s', '%s')"

  try:

  cur.execute(sql % (indexs, keywords))

  except MySQLdb.Error, e:

  print 'MySql error', e

  continue

  except TypeError, e:

  print 'TypeError, Pass' , e

  continue

  print 'done to mysql'

  else:

  print '唯有两种导出方式,请输入1或许2'

  复制代码

  运用方式:

  1、将你的词根放到sourceword.txt 中,一行一个词,而后将本文代码随便保存成一个xxxx.py 和sourceword.txt 放在同一个目次下。

  2、交互模式下,进入这两个文件地点目次,运转脚本xxx.py(通常是输入python xxx.py能够)

  3、会有提醒选择导出模式,1为导出txt文件,2为导入到mysql中。如下图

  假如需求导入到mysql中,请配置mysql的关联信息,在代码中有说明注解。

  不过首先需求在你的数据库中创立一个表,语句如下:

  CREATE TABLE `shangqing_keyword` (

  `id` int(11) unsigned NOT NULL AUTO_INCREMENT,

  `keyword` varchar(200) DEFAULT NULL,

  `total` int(11) DEFAULT NULL,

  PRIMARY KEY (`id`),

  UNIQUE KEY `keyword` (`keyword`)

  ) ENGINE=MyISAM AUTO_INCREMENT=1 DEFAULT CHARSET=utf8;

  4、等候完毕。

  个体以为导入到mysql更好处理,txt对照好处理一些。

  我的sourceword中有6000个词,挖走出差不多30多万我就停止了。应当能挖走出更多。

  导入到mysql是如此的。仍然mysql用起来随手一些。个体爱好。

  关注:导出txt格式是存在反复词的,因为我不晓得何如去过滤。可是导入到mysql中 反复词是会自动过滤掉的。不过反正都无所谓,晚期处理的时辰众人总能找到方式的。

转载请注明出处。