Python Query Baidu SEO information

A simple python query Baidu keyword ranking function, features:

1. UA Random

2, the operation is simple and convenient, direct getrank (keywords, domain name) can be

3, code conversion. There should be no problem with coding.

4, the result is rich. Not only rankings, but also search results title,url, snapshot time, in line with SEO requirements

Disadvantages:

Single thread, slow speed

#coding =utf-8 Import Requestsimport beautifulsoupimport reimport random def Decodeanyword (W): Try:w.decode (' u Tf-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 (', ' + '). Repla CE (' \ n ', ') Baiduurl = ' http://www.baidu.com/s?wd=%s&rn=100 '% checkword return baiduurl def getcontent (Baiduu RL): #get The content of the serp ualist = [' mozilla/4.0+ (compatible;+msie+6.0;+windows+nt+5.1;+sv1;+.net+clr+1.1.432 2;+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)} iplist = [' 202.43.188.13:8080 ', ' 80.243. 185.168:1177 ', ' 218.108.85.59:81 '] proxies = {' http ': ' http://%s '% Random.choice (iplist)} r = Requests.get (Baidu URL, headers = headers, proxies = proxies) return r.content def getlasturl (rawurl): #get final URL while there ' re Redi Rects r = Requests.get (Rawurl) return R.url def getatext (atext): #get the text with and Pat = Re.compile (R '    (.*?)') Match = Pat.findall (atext) PureText = Match[0].replace ('' , '). Replace ('', ') return PureText def getcachedate (t): #get The date of the 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 Ch  Eckword = 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): #改正则 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)) #g ET the cache date of the Target page res = U '%s, first%s name,%s,%s,%s '% (Checkword, Nowrank, Restitle, Cachedate, Domainurl) Return Res.encode (' gb2312 ') break Else:return ' >100 ' domain = ' www.douban.com ' #set the domain W      Hich want to search. f = open (' R.txt ') for W in F.readlines (): Print GetRank (w, domain) F.close ()

