快捷導(dǎo)航

python實(shí)現(xiàn)百度關(guān)鍵詞排名查詢(xún)

更新時(shí)間：2014年03月30日 10:29:08 作者：

這篇文章主要介紹了python實(shí)現(xiàn)百度關(guān)鍵詞排名查詢(xún),需要的朋友可以參考下

就是一個(gè)簡(jiǎn)單的python查詢(xún)百度關(guān)鍵詞排名的函數(shù)，以下是一些簡(jiǎn)介：
1、UA隨機(jī)
2、操作簡(jiǎn)單方便，直接getRank(關(guān)鍵詞，域名)就可以了
3、編碼轉(zhuǎn)化。編碼方面應(yīng)該沒(méi)啥問(wèn)題了。
4、結(jié)果豐富。不僅有排名，還有搜索結(jié)果的title，URL，快照時(shí)間，符合SEO需求
5、拿來(lái)做個(gè)軟件或者自己用都很方便。

功能是單線(xiàn)程實(shí)現(xiàn)，速度慢，大家可以參考修改成自己需要的。

復(fù)制代碼代碼如下:

#coding=utf-8

import requests
import BeautifulSoup
import re
import random

def decodeAnyWord(w):
    try:
        w.decode('utf-8')
    except:
        w = w.decode('gb2312')
    else:
        w = w.decode('utf-8')
    return w

def createURL(checkWord):   #create baidu URL with search words
    checkWord = checkWord.strip()
    checkWord = checkWord.replace(' ', '+').replace('\n', '')
    baiduURL = 'http://www.baidu.com/s?wd=%s&rn=100' % checkWord
    return baiduURL

def getContent(baiduURL):   #get the content of the serp
    uaList = ['Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+1.1.4322;+TencentTraveler)',
    'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+2.0.50727;+.NET+CLR+3.0.4506.2152;+.NET+CLR+3.5.30729)',
    'Mozilla/5.0+(Windows+NT+5.1)+AppleWebKit/537.1+(KHTML,+like+Gecko)+Chrome/21.0.1180.89+Safari/537.1',
    'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1)',
    'Mozilla/5.0+(Windows+NT+6.1;+rv:11.0)+Gecko/20100101+Firefox/11.0',
    'Mozilla/4.0+(compatible;+MSIE+8.0;+Windows+NT+5.1;+Trident/4.0;+SV1)',
    'Mozilla/4.0+(compatible;+MSIE+8.0;+Windows+NT+5.1;+Trident/4.0;+GTB7.1;+.NET+CLR+2.0.50727)',
    'Mozilla/4.0+(compatible;+MSIE+8.0;+Windows+NT+5.1;+Trident/4.0;+KB974489)']
    headers = {'User-Agent': random.choice(uaList)}

r = requests.get(baiduURL, headers = headers)
return r.content

def getLastURL(rawurl): #get final URL while there're redirects
r = requests.get(rawurl)
return r.url

def getAtext(atext): #get the text with <a> and </a>
 pat = re.compile(r'<a .*?>(.*?)</a>')
 match = pat.findall(atext.replace('\n', ''))
 pureText = match[0].replace('', '').replace('', '')
 return pureText.replace('\n', '')

def getCacheDate(t): #get the date of cache
 pat = re.compile(r'.*?(\d{4}-\d{1,2}-\d{1,2}) ')
 match = pat.findall(t)
 cacheDate = match[0]
 return cacheDate

def getRank(checkWord, domain): #main line
    checkWord = checkWord.replace('\n', '')
    checkWord = decodeAnyWord(checkWord)
    baiduURL = createURL(checkWord)
    cont = getContent(baiduURL)
    soup = BeautifulSoup.BeautifulSoup(cont)
    results = soup.findAll('table', {'class': 'result'})    #find all results in this page

for result in results:
 checkData = unicode(result.find('span', {'class': 'g'}))
 if re.compile(r'^[^/]*%s.*?' %domain).match(checkData.replace('', '').replace('', '')): #改正則
 nowRank = result['id'] #get the rank if match the domain info

            resLink = result.find('h3').a
            resURL = resLink['href']
            domainURL = getLastURL(resURL) #get the target URL
            resTitle = getAtext(unicode(resLink))   #get the title of the target page

rescache = result.find('span', {'class': 'g'})
cacheDate = getCacheDate(unicode(rescache)) #get the cache date of the target page

            res = u'%s, 第%s名, %s, %s, %s' % (checkWord, nowRank, resTitle, cacheDate, domainURL)
            return res.encode('gb2312')
            break
    else:
        return '>100'

domain = 'www.baidu.com' #set the domain which you want to search.
print getRank('百度', domain)

您可能感興趣的文章: