python关键词挖掘_Python登录采集案例，爱站关键词挖掘采集seo工具源码

#爱站关键词挖掘

import requests

from lxml import etree

import time

import xlwt

headers = {

s = requests.Session()

#登陆账号

def dlwz():

url = 'https://www.aizhan.com/login.php'

html = s.get(url, headers=headers).text

# print(html)

con = etree.HTML(html)

# print(con)

# 获取验证码参数

parameter = con.xpath('//ul[@class="auth-login"]/li/img/@src')[0]

print(parameter)

# 获取验证码图片地址

img_url = f'https://www.aizhan.com/{parameter}'

print(img_url)

# 下载验证码图片到本地

r_img = s.get(img_url)

with open('https://blog.csdn.net/weixin_39997695/article/details/yanzhengma.jpg', 'wb') as fp:

fp.write(r_img.content)

# 输入验证码

code = input('请输入验证码:')

password= input('请输入密码:')

data = {

'refer': 'https://ci.aizhan.com/',

'username': '2504520968@qq.com',

'password': password,

'code': code

r = s.post(url, headers=headers, data=data)

if "退出" in r.text:

print("登陆成功！")

else:

print("登陆失败！验证码错误？账号输入有误？")

#获取关键词页码

def get_keyword_num(keyword_url):

url=f"https://ci.aizhan.com/{keyword_url}/"

print(con)

page=con.xpath('//div[@class="pager"]/ul/li/a/text()')

print(page)

return page

#cookies登陆

def cookdl(cookie):

head={

'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',

'Accept-Encoding': 'gzip, deflate, br',

'Accept-Language': 'zh-CN,zh;q=0.9',

'Cache-Control': 'max-age=0',

'Connection': 'keep-alive',

'cookie': cookie,

'Host': 'ci.aizhan.com',

'Referer': 'https://ci.aizhan.com/',

'Upgrade-Insecure-Requests': '1',

get_url="https://ci.aizhan.com/5de54e1a8bbe8ba1/"

req=requests.get(get_url,headers=head)

print(req)

print(req.text)

#关键词url编码

def get_keyword_url(keyword):

'''http://static.aizhan.com/js/home.js'''

s = ""

if keyword:

keyword = keyword.replace('+', '')

for c in keyword:

e = hex(ord(c))[2:]

if len(e) == 2:

e = "n" + e

s += e

def get_keyword_data(keyword_url,num):

data_list=[]

url=f"https://ci.aizhan.com/{keyword_url}/{num}/"

time.sleep(5)

key_words=con.xpath('//table[@class="table table-striped table-s2"]/tbody/tr/td[@class="title"]/a/@title') #获取关键词

print(key_words)

print(len(key_words))

pc_mobile_indexs=con.xpath('//table[@class="table table-striped table-s2"]/tbody/tr/td[@class="center"]/span/text()') #获取PC/移动指数

print(pc_mobile_indexs)

print(len(pc_mobile_indexs))

inclusions=con.xpath('//table[@class="table table-striped table-s2"]/tbody/tr/td[@class="level"]/text()') #获取收录数

print(inclusions)

print(len(inclusions))

hrefs=con.xpath('//table[@class="table table-striped table-s2"]/tbody/tr/td[@class="url"]/a/i/text()') #获取首页一二位链接

first_hrefs=hrefs[::2] #首页第一位置链接

print(first_hrefs)

print(len(first_hrefs))

second_hrefs=hrefs[1::2] #首页第二位置链接

print(second_hrefs)

print(len(second_hrefs))

titles=con.xpath('//table[@class="table table-striped table-s2"]/tbody/tr/td[@class="url"]/a/p/text()') #获取首页一二位标题

first_titles=titles[::2] #首页第一位置标题

print(first_titles)

print(len(first_titles))

second_titles=titles[1::2] #首页第二位置标题

print(second_titles)

print(len(second_titles))

for key_word,pc_mobile_index,inclusion,first_href,first_title,second_href,second_title in zip (

key_words,pc_mobile_indexs,inclusions,first_hrefs,first_titles,second_hrefs,second_titles):

data=[

key_word,

pc_mobile_index,

inclusion,

first_href,

first_title,

second_href,

second_title,

]

print(data)

data_list.append(data)

#print(data_list)

#print(len(data_list))

return data_list

#保存关键词数据为excel格式

def bcsj(keyword,data):

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

booksheet = workbook.add_sheet(f'{keyword}', cell_overwrite_ok=True)

title = [['关键词', 'PC/移动指数', '收录数', '首页第1位链接', '首页第1位标题','首页第2位链接', '首页第2位标题']]

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"保存关键词数据为{keyword}.xls 成功！")

if __name__ == '__main__':

keyword = input('请输入关键词>>')

dlwz()

keyword_url=get_keyword_url(keyword)

page_num=get_keyword_num(keyword_url)

datas_list=[]

for num in page_num:

print(num)

print(f'正在查询采集第{num}页关键词挖掘数据！')

data_list=get_keyword_data(keyword_url, num)

datas_list.extend(data_list)

print(datas_list)

本文地址：http://syank.xrbh.cn/quote/6836.html    迅博思语资讯 http://syank.xrbh.cn/ , 查看更多