本帖最后由 刀心 于 2015-6-26 17:43 编辑
前段时间在@方法的博客上看到一个数据接口,貌似是百度商情的关键词数据。
方法博客中用的是ssh,几行代码就搞定了挖词,但是我试了一下,挖出来有一些错乱也有一些重复。于是就用python做了一个版本。拿出来分享一下。
方法的原文:http://seofangfa.com/shell/baidukeyword-shangqing.html
在运行脚本之前,请确定你是否按照了MySQLdb库,安装方法可以去百度一下。
下面是我的代码。
- #!/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')
- #useragent 列表,大家可以自行去收集。不过在本例中似乎不需要这个
- 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)
- #如果需要把挖出来的关键词保存到数据库,需要配置数据库相关信息
- 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' #数据库密码
- 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方法是从@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("请选择导出形式;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 '只有两种导出方式,请输入1或者2'
复制代码
使用方法:
1、将你的词根放到sourceword.txt 中,一行一个词,然后将本文代码随便保存成一个xxxx.py 和sourceword.txt 放在同一个目录下。
2、交互模式下,进入这两个文件所在目录,运行脚本xxx.py(一般是输入python xxx.py即可)
3、会有提示选择导出模式,1为导出txt文件,2为导入到mysql中。如下图
图中的typeerror请忽略。
如果需要导入到mysql中,请配置mysql的相关信息,在代码中有注释。
不过首先需要在你的数据库中创建一个表,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;
复制代码
4、等待完成。
个人认为导入到mysql更好管理,txt比较好处理一些。
我的sourceword中有6000个词,挖出来差不多30多万我就停止了。应该能挖出来更多。
效果截图:
这个是导出为txt格式的样子。
导入到mysql是这样的。还是mysql用起来顺手一些。个人喜好。
注意:导出txt格式是存在重复词的,因为我不知道怎么去过滤。但是导入到mysql中 重复词是会自动过滤掉的。不过反正都无所谓,后期处理的时候大家总能找到办法的。
如果使用有什么问题,欢迎交流。
|