網(wǎng)站關鍵詞查詢挖掘，包括三大常用網(wǎng)站seo查詢工具站點，愛站，站長，以及5118，其中，愛站及站長最多可查詢到50頁，5118可查詢到100頁，如果想要查詢完整網(wǎng)站關鍵詞排名數(shù)據(jù)，需充值購買會員，當然免費的查詢也是需要注冊會員的，不然也是沒有查詢權限！
5118
須自行補齊網(wǎng)站地址及Cookie協(xié)議頭，查詢需要登陸權限！
#?5118網(wǎng)站關鍵詞采集
#?-*-?coding:?utf-8?-*-
import?requests
from?lxml?import?etree
import?time
import?logging
logging.basicConfig(filename='s5118.log',?level=logging.DEBUG,format='%(asctime)s?-?%(levelname)s?-?%(message)s')
#獲取關鍵詞
def?get_keywords(site,page):
????url="https://www.5118.com/seo/baidupc"
????headers={
????????"Cookie":Cookie,
????????"User-Agent":?"Mozilla/5.0?(Windows?NT?6.1;?WOW64)?AppleWebKit/537.36?(KHTML,?like?Gecko)?Chrome/86.0.4240.198?Safari/537.36",
????}
????data={
????????"isPager":?"true",
????????"viewtype":?2,
????????"days":?90,
????????"url":?site,
????????"orderField":?"Rank",
????????"orderDirection"?:?"sc",
????????"pageIndex":?page,
????????"catalogName":?"",
????????"referKeyword":?"",
????}
????response=requests.post(url=url,data=data,headers=headers,timeout=10)
????print(response.status_code)
????html=response.content.decode('utf-8')
????tree=etree.HTML(html)
????keywords=tree.xpath('//td[@class="list-col?justify-content?"]/a[@class="w100?all_array"]/text()')
????print(keywords)
????save_txt(keywords,?site)
????return?keywords
#存儲為csv文件
def?save_csv(keywords,site):
????filename=site.replace("www.",'').replace(".com",'').replace(".cn",'').replace('https://','').replace('http://','')
????for?keyword?in?keywords:
????????with?open(f'5118_{filename}.csv','a+',encoding='utf-8-sig')?as?f:
????????????f.write(f'{keyword}\n')
????print("保存關鍵詞列表成功！")
#存儲為txt文件
def?save_txt(keywords,site):
????filename=site.replace("www.",'').replace(".com",'').replace(".cn",'').replace('https://','').replace('http://','')
????for?keyword?in?keywords:
????????with?open(f'5118_{filename}.txt','a+',encoding='utf-8')?as?f:
????????????f.write(f'{keyword}\n')
????print("保存關鍵詞列表成功！")
def?main(site):
????logging.info(f"開始爬取網(wǎng)站{site}關鍵詞數(shù)據(jù)..")
????num?=?100
????keys=[]
????for?page?in?range(1,num+1):
????????print(f"正在爬取第{page}頁數(shù)據(jù)..")
????????logging.info(f"正在爬取第{page}頁數(shù)據(jù)..")
????????try:
????????????keywords?=?get_keywords(site,?page)
????????????keys.extend(keywords)
????????????time.sleep(8)
????????except?Exception?as?e:
????????????print(f"爬取第{page}頁數(shù)據(jù)失敗--錯誤代碼：{e}")
????????????logging.error(f"爬取第{page}頁數(shù)據(jù)失敗--錯誤代碼：{e}")
????????????time.sleep(10)
????keys?=?set(keys)??#去重
????save_csv(keys,?site)
if?__name__?==?'__main__':
????site=""
????main(site)
愛站
須自行補齊網(wǎng)站地址及Cookie協(xié)議頭，查詢需要登陸權限！
#?愛站網(wǎng)站關鍵詞采集
#?-*-?coding:?utf-8?-*-
import?requests
from?lxml?import?etree
import?time
import?logging
logging.basicConfig(filename='aizhan.log',?level=logging.DEBUG,format='%(asctime)s?-?%(levelname)s?-?%(message)s')
#獲取關鍵詞
def?get_keywords(site,page):
????url=f"https://baidurank.aizhan.com/baidu/{site}/-1/0/{page}/position/1/"
????headers?=?{
????????"Cookie":Cookie?,
????}
????response?=?requests.get(url=url,headers=headers,?timeout=10)
????print(response.status_code)
????html?=?response.content.decode('utf-8')
????tree?=?etree.HTML(html)
????keywords?=?tree.xpath('//td[@class="title"]/a[@class="gray"]/@title')
????print(keywords)
????save_txt(keywords,?site)
????return?keywords
#存儲為csv文件
def?save_csv(keywords,site):
????filename=site.replace("www.",'').replace(".com",'').replace(".cn",'').replace('https://','').replace('http://','')
????for?keyword?in?keywords:
????????with?open(f'aizhan_{filename}.csv','a+',encoding='utf-8-sig')?as?f:
????????????f.write(f'{keyword}\n')
????print("保存關鍵詞列表成功！")
#存儲為txt文件
def?save_txt(keywords,site):
????filename=site.replace("www.",'').replace(".com",'').replace(".cn",'').replace('https://','').replace('http://','')
????for?keyword?in?keywords:
????????with?open(f'aizhan_{filename}.txt','a+',encoding='utf-8')?as?f:
????????????f.write(f'{keyword}\n')
????print("保存關鍵詞列表成功！")
def?main(site):
????logging.info(f"開始爬取網(wǎng)站{site}關鍵詞數(shù)據(jù)..")
????num?=?50
????keys=[]
????for?page?in?range(1,num+1):
????????print(f"正在爬取第{page}頁數(shù)據(jù)..")
????????logging.info(f"正在爬取第{page}頁數(shù)據(jù)..")
????????try:
????????????keywords?=?get_keywords(site,?page)
????????????keys.extend(keywords)
????????????time.sleep(8)
????????except?Exception?as?e:
????????????print(f"爬取第{page}頁數(shù)據(jù)失敗--錯誤代碼：{e}")
????????????logging.error(f"爬取第{page}頁數(shù)據(jù)失敗--錯誤代碼：{e}")
????????????time.sleep(10)
????keys?=?set(keys)??#去重
????save_csv(keys,?site)
if?__name__?==?'__main__':
????site=""
????main(site)
站長
須自行補齊網(wǎng)站地址及Cookie協(xié)議頭，查詢需要登陸權限！
#?站長之家網(wǎng)站關鍵詞采集
#?-*-?coding:?utf-8?-*-
import?requests
from?lxml?import?etree
import?time
import?logging
logging.basicConfig(filename='chinaz.log',?level=logging.DEBUG,format='%(asctime)s?-?%(levelname)s?-?%(message)s')
#獲取關鍵詞
def?get_keywords(site,page):
????headers={
????????"Cookie":Cookie,
????????"User-Agent":?"Mozilla/5.0?(Windows?NT?6.1;?WOW64)?AppleWebKit/537.36?(KHTML,?like?Gecko)?Chrome/86.0.4240.198?Safari/537.36",
????}
????url=f"https://rank.chinaz.com/{site}-0---0-{page}"
????response=requests.get(url=url,headers=headers,timeout=8)
????print(response)
????html=response.content.decode('utf-8')
????tree=etree.HTML(html)
????keywords=tree.xpath('//ul[@class="_chinaz-rank-new5b"]/li[@class="w230?"]/a/text()')
????print(keywords)
????save_txt(keywords,?site)
????return?keywords
#存儲為csv文件
def?save_csv(keywords,site):
????filename=site.replace("www.",'').replace(".com",'').replace(".cn",'').replace('https://','').replace('http://','')
????for?keyword?in?keywords:
????????with?open(f'chinaz_{filename}.csv','a+',encoding='utf-8-sig')?as?f:
????????????f.write(f'{keyword}\n')
????print("保存關鍵詞列表成功！")
#存儲為txt文件
def?save_txt(keywords,site):
????filename=site.replace("www.",'').replace(".com",'').replace(".cn",'').replace('https://','').replace('http://','')
????for?keyword?in?keywords:
????????with?open(f'chinaz_{filename}.txt','a+',encoding='utf-8')?as?f:
????????????f.write(f'{keyword}\n')
????print("保存關鍵詞列表成功！")
def?main(site):
????logging.info(f"開始爬取網(wǎng)站{site}關鍵詞數(shù)據(jù)..")
????num?=?50
????keys=[]
????for?page?in?range(1,num+1):
????????print(f"正在爬取第{page}頁數(shù)據(jù)..")
????????logging.info(f"正在爬取第{page}頁數(shù)據(jù)..")
????????try:
????????????keywords?=?get_keywords(site,?page)
????????????keys.extend(keywords)
????????????time.sleep(8)
????????except?Exception?as?e:
????????????print(f"爬取第{page}頁數(shù)據(jù)失敗--錯誤代碼：{e}")
????????????logging.error(f"爬取第{page}頁數(shù)據(jù)失敗--錯誤代碼：{e}")
????????????time.sleep(10)
????keys?=?set(keys)??#去重
????save_csv(keys,?site)
if?__name__?==?'__main__':
????site=""
????main(site)往期推薦:
Python爬蟲三種解析方式帶你360搜索排名查詢
Python與Seo工具全網(wǎng)搜錄查詢助手exe
Python百度下拉框關鍵詞采集工具
Python制作sitemap.xml文件工具源碼
Python調(diào)用翻譯API接口實現(xiàn)“智能”偽原創(chuàng)
百度快排之Python selenium 實現(xiàn)搜索訪問目標網(wǎng)站
·················END·················
你好，我是二大爺，
革命老區(qū)外出進城務工人員，
互聯(lián)網(wǎng)非早期非專業(yè)站長，
喜好python，寫作，閱讀，英語
不入流程序，自媒體，seo . . .
公眾號不掙錢，交個網(wǎng)友。
讀者交流群已建立，找到我備注 “交流”，即可獲得加入我們~
聽說點 “在看” 的都變得更好看吶~
關注關注二大爺唄~給你分享python，寫作，閱讀的內(nèi)容噢~
掃一掃下方二維碼即可關注我噢~
關注我的都變禿了
說錯了，都變強了！
不信你試試
掃碼關注最新動態(tài)文章來源：http://www.zghlxwxcb.cn/news/detail-495562.html
公眾號ID：eryeji文章來源地址http://www.zghlxwxcb.cn/news/detail-495562.html
到了這里，關于Python與SEO，三大SEO網(wǎng)站查詢工具關鍵詞查詢采集源碼！的文章就介紹完了。如果您還想了解更多內(nèi)容，請在右上角搜索TOY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關文章，希望大家以后多多支持TOY模板網(wǎng)！
