sqte 046「百度排名查问」【python】百度关头词排名查问完成

百度排名查问

Python版本：3.7.1

装置依靠包requests re urllib bs4......

装置方式：翻开python装置目次，找到scripts的目次，按住shift呈现翻开号令窗口，进入后先pip list检查装置了那些包，而后再pip install 装置所须要的包。

参考网址：http://blog.csdn.net/Ryuchong/article/details/80687447

# -*- coding:utf8 -*-
import requests
import re
import pymysql

#关头字，公司网址，查问网址
keyword = input(u"请输出你要查问的关头字")
site = input("请输出您要查问的网址")
site_baidu = u"http://www.baidu.com/s?wd=%s&pn=%d0"
site_360 = "http://hao.360.cn/"


#查问排名
i = 0
#word = u"体检行业爆丑闻"
#site = "http://baijiahao.baidu.com"
site_baidu = u"http://www.baidu.com/s?wd=%s&pn=%d0"
def keywordRank(searchTxt, webUrl):
    global i
    try:
        pattern = re.compile(b'class="c-showurl" style="text-decoration:none;">(.*?)&nbsp', re.S)
        result = pattern.findall(searchTxt)
        for item in result:
            item_str = str(item, encoding = "utf8")
            i = i+1
            print ("rank %d: %s"%(i,item_str))
            if site  in item_str:
                return i
    except Exception as e:
        print(e)
       
        return None
    return None
 
# content:要搜刮的关头词, page:要搜刮的页码
def BaiduSearch(content, page):
    try:
        url = site_baidu % (content, page)
        data = requests.get(url)
        return data.content
    except Exception as e:
        return None
     
if __name__ == "__main__":
    loops = 10     # 最多查到第 10 页
    page = 0
    while(loops):
        searchTxt = BaiduSearch(keyword, page)
        page = page+1
        rank = KeywordRank(searchTxt, site)
        if None!=rank:
            print (u"输出的关头词排在第 %d 名" % rank)
            print(rank)
            break
        loops = loops - 1


#数据库毗连存储数据
        
conn = pymysql.Connect(
    host = '127.0.0.1',
    port = 3306,
    user = 'root',
    password = 'root',
    db = 'test',
    charset = 'utf8'
    )

cursor = conn.cursor()

sql_insert="insert into 搜刮引擎优化(id,site,word,rank) values('','%s','%s','%d')"%(site,keyword,rank)
cursor.execute(sql_insert)
conn.commit()
cursor.close()
conn.close()