过程：
1）先把一篇文章，按逗号分隔成一个一个短语
2）然后计算每个短语的字数
3）前两个>10个字的短语，我们拿出来在百度搜索下，计算百度搜索结果中，完整出现该短语的次数。
若一个文章被其他网站大量转载，那么随便提取该文章中一个短语，都能在百度搜索出完全重复的内容：
如果我们连续搜索两个短语，在百度搜索中，完全重复的结果很少，则可以一定程度代表该内容被其他站点大量转载的概率比较小，原创度较高
原创
以上3个步骤，编写一个脚本来执行：
左列是文章ID，右列是两个短语，在百度搜索结果中完整出现的次数。次数越大，重复度越高，具体数值达到多少，自己定义。比如本渣一般将>=30%定位重复度比较高的，即搜索2个短语，20个搜索结果中，完整出现该短语的结果有>=6个
#coding:utf-8
import requests,re,time,sys,json,datetime
import multiprocessing
import MySQLdb as mdb
reload(sys)
sys.setdefaultencoding('utf-8')
current_date = time.strftime('%Y-%m-%d',time.localtime(time.time()))
def search(req,html):
text = re.search(req,html)
if text:
data = text.group(1)
else:
data = 'no'
return data
def date(timeStamp):
timeArray = time.localtime(timeStamp)
otherStyleTime = time.strftime("%Y-%m-%d %H:%M:%S", timeArray)
return otherStyleTime
def getHTml(url):
host = search('^([^/]*?)/',re.sub(r'(https|http):
headers = {
"Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
"Accept-Encoding":"gzip, deflate, sdch",
"Accept-Language":"zh-CN,zh;q=0.8,en;q=0.6",
"Cache-Control":"no-cache",
"Connection":"keep-alive",
#"Cookie":"",
"Host":host,
"Pragma":"no-cache",
"Upgrade-Insecure-Requests":"1",
"User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36",
}
# 代理服务器
proxyHost = "proxy.abuyun.com"
proxyPort = "9010"
# 代理隧道验证信息
proxyUser = "XXXX"
proxyPass = "XXXX"
proxyMeta = "http://%(user)s:%(pass)s@%(host)s:%(port)s" % {
"host" : proxyHost,
"port" : proxyPort,
"user" : proxyUser,
"pass" : proxyPass,
}
proxies = {
"http" : proxyMeta,
"https" : proxyMeta,
}
html = requests.get(url,headers=headers,timeout=30)
# html = requests.get(url,headers=headers,timeout=30,proxies=proxies)
code = html.encoding
return html.content
def getContent(word):
pcurl = 'http:
# print '@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ start crawl %s @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@' % pcurl
html = getHTml(pcurl)
a = 0
html_dict = json.loads(html)
for tag in html_dict['feed']['entry']:
if tag.has_key('title'):
title = tag['title']
url = tag['url']
rank = tag['pn']
time = date(tag['time'])
abs = tag['abs']
if word in abs:
a += 1
return a
con = mdb.connect('127.0.0.1','root','','wddis',charset='utf8',unix_socket='/tmp/mysql.sock')
cur = con.cursor()
with con:
cur.execute("select aid,content from pre_portal_article_content limit 10")
numrows = int(cur.rowcount)
for i in range(numrows):
row = cur.fetchone()
aid = row[0]
content = row[1]
content_format = re.sub('<[^>]*?>','',content)
a = 0
for z in [ x for x in content_format.split('，') if len(x)>10 ][:2]:
a += getContent(z)
print "%s --> %s" % (aid,a)
# words = open(wordfile).readlines()
# pool = multiprocessing.Pool(processes=10)
# for word in words:
# word = word.strip()
# pool.apply_async(getContent, (word,client ))
# pool.close()
# pool.join()
