采集數(shù)據(jù)來源于站長之家！

需要輸入關(guān)鍵詞！

引用的庫

import?requests

from?lxml?import?etree

import?re

import?xlwt

import?time

例子：

1.etree采集列表

2.切片操作

3.保存excel格式

#站長工具關(guān)鍵詞挖掘

# -*- coding=utf-8 -*-

import requests

from lxml import etree

import re

import xlwt

import time

headers={

'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/534.55.3 (KHTML, like Gecko) Version/5.1.3 Safari/534.53.10'

}

#查詢關(guān)鍵詞是否能找到相關(guān)的關(guān)鍵字

def search_keyword(keyword):

data={

'kw': keyword,

'page': '1',

'by': '0',

}

url="http://stool.chinaz.com/baidu/words.aspx"

html=requests.post(url,data=data,headers=headers).text

time.sleep(3)

#print(html)

con=etree.HTML(html)

key_result=con.xpath('//div[@class="col-red lh30 fz14 tc"]/text()')

try:

key_result=key_result[0] #沒有找到相關(guān)的關(guān)鍵字

except:

key_result=[]

#print(key_result)

return key_result

#獲取關(guān)鍵詞頁碼數(shù)和記錄條數(shù)

def get_page_number(keyword):

data = {

'kw': keyword,

'page': '1',

'by': '0',

}

url = "http://stool.chinaz.com/baidu/words.aspx"

html = requests.post(url, data=data, headers=headers).text

time.sleep(3)

# print(html)

con = etree.HTML(html)

page_num = con.xpath('//span[@class="col-gray02"]/text()')

page_numberze = r'共(.+?)頁'

page_number = re.findall(page_numberze, page_num[0], re.S)

page_number = page_number[0]

#print(page_number)

total_data = con.xpath('//p[@class="col-gray lh24 fr pr5"]') # 數(shù)據(jù)記錄

total_datas = total_data[0].xpath('string(.)') # 獲取節(jié)點(diǎn)所有文本

#print(total_datas)

print(f'挖掘關(guān)鍵詞：{keyword}-{total_datas}')

return page_number

#獲取關(guān)鍵詞數(shù)據(jù)

def get_keyword_datas(keyword,page_number):

datas_list = []

for i in range(1,page_number+1):

print(f'正在采集第{i}頁關(guān)鍵詞挖掘數(shù)據(jù)...')

data = {

'kw': keyword,

'page': i,

'by': '0',

}

#print(data)

url = "http://stool.chinaz.com/baidu/words.aspx"

html = requests.post(url, data=data, headers=headers).text

time.sleep(3)

#print(html)

con = etree.HTML(html)

key_words = con.xpath('//p[@class="midImg"]/a/span/text()') # 關(guān)鍵詞

#print(key_words)

keyword_all_datas = []

keyword_datas = con.xpath('//ul[@class="ResultListWrap "]/li/div[@class="w8-0"]/a')

for keyword_data in keyword_datas:

keyword_data = keyword_data.text

if keyword_data != None:

keyword_all_datas.append(keyword_data)

#print(keyword_all_datas)

overall_indexs = keyword_all_datas[0::5] # 整體指數(shù)

#print(overall_indexs )

pc_indexs = keyword_all_datas[1::5] # pc指數(shù)

#print(pc_indexs)

mobile_indexs = keyword_all_datas[2::5] # 移動(dòng)指數(shù)

#print(mobile_indexs)

s360_indexs = keyword_all_datas[3::5] # 360指數(shù)

#print(s360_indexs)

collections = keyword_all_datas[4::5] # 收錄量

#print(collections)

ips = con.xpath('//ul[@class="ResultListWrap "]/li/div[@class="w15-0 kwtop"]/text()') # 預(yù)估流量

if ips==[]:

ips =['--']

#print(ips)

first_place_hrefs = con.xpath(

'//ul[@class="ResultListWrap "]/li/div[@class="w18-0 lh24 tl"]/a/text()') # 首頁位置鏈接

if first_place_hrefs==[]:

first_place_hrefs=con.xpath('//ul[@class="ResultListWrap "]/li/div[@class="w18-0 lh24 tl"]/text()')

#print(first_place_hrefs)

first_place_titles = con.xpath(

'//ul[@class="ResultListWrap "]/li/div[@class="w18-0 lh24 tl"]/p[@class="lh17 pb5"]/text()') # 首頁位置標(biāo)題

if first_place_titles == []:

first_place_titles=['--']

#print(first_place_titles)

data_list = []

for key_word, overall_index, pc_index, mobile_index, s360_index, collection, ip, first_place_href, first_place_title in zip(

key_words, overall_indexs, pc_indexs, mobile_indexs, s360_indexs, collections, ips, first_place_hrefs,

first_place_titles

):

data = [

key_word,

overall_index,

pc_index,

mobile_index,

s360_index,

collection,

ip,

first_place_href,

first_place_title,

]

print(data)

print('\n')

data_list.append(data)

time.sleep(3)

datas_list.extend(data_list) #合并關(guān)鍵詞數(shù)據(jù)

return datas_list

#保存關(guān)鍵詞數(shù)據(jù)為excel格式

def bcsj(keyword,data):

workbook = xlwt.Workbook(encoding='utf-8')

booksheet = workbook.add_sheet('Sheet 1', cell_overwrite_ok=True)

title = [['關(guān)鍵詞', '整體指數(shù)', 'PC指數(shù)', '移動(dòng)指數(shù)', '360指數(shù)', '預(yù)估流量（ip）', '收錄量', '網(wǎng)站首位鏈接', '網(wǎng)站首位標(biāo)題']]

title.extend(data)

#print(title)

for i, row in enumerate(title):

for j, col in enumerate(row):

booksheet.write(i, j, col)

workbook.save(f'{keyword}.xls')

print(f"保存關(guān)鍵詞數(shù)據(jù)為 {keyword}.xls 成功！")

if __name__ == '__main__':

keyword = input('請輸入關(guān)鍵詞>>')

print('正在查詢，請稍后...')

result=search_keyword(keyword)

if result=="沒有找到相關(guān)的關(guān)鍵字":

print('\n')

print (result)

print("該關(guān)鍵詞沒有挖掘到關(guān)鍵詞數(shù)據(jù)")

else:

print('\n')

page_number=get_page_number(keyword)

print('\n')

print('正在采集關(guān)鍵詞挖掘數(shù)據(jù)，請稍后...')

print('\n')

page_number=int(page_number)

datas_list=get_keyword_datas(keyword,page_number)

print('\n')

print('關(guān)鍵詞挖掘數(shù)據(jù)采集結(jié)果：')

print('========================采集結(jié)果========================\n\n')

for datas in datas_list:

print(datas)

print('\n\n========================采集結(jié)束========================\n')

bcsj(keyword, datas_list)

總結(jié)

以上是生活随笔為你收集整理的python关键词挖掘_seo必备工具，python采集关键词挖掘数据的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。