Python与seo工具脚本，360/搜狗相关搜索词采集源码参考

re.findall(r'<a data-ext=".+?" href=".+?">(.+?)</a>', html, re.S | re.I)

re.findall(r'<p><a href=".+?" id="sogou_99999_.+?">(.+?)</a></p>', html, re.S | re.I)

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
360相关搜索词挖掘脚本（多线程版）
基于python3.8
需要安装requests模块
@author：微信/huguo00289
"""
import re

from queue import Queue

from threading import Thread

import requests,random
class Qh360Spider(Thread):

result = {}  # 保存结果字典

seen = set()  # 表示在队列中的关键词（已抓取或待抓取）
def __init__(self, kw_queue, loop, failed):
    super(Qh360Spider, self).__init__()
    self.kw_queue = kw_queue  # 关键词队列
    self.loop = loop  # 循环挖词拓展次数
    self.failed = failed  # 保存查询失败的关键词文件
    self.ua_list = [
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1',
        'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36Chrome 17.0',
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11',
        'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101 Firefox/6.0Firefox 4.0.1',
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
        'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
        'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
        'Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11',
    ]


def run(self):  # 程序的执行流程
    while True:
        # 从队列里面获取一个关键词及其对应的当前拓展次数
        kw, cloop = self.kw_queue.get()
        print('CurLoop:{} Checking: {}'.format(cloop, kw))
        query = 'https://www.so.com/s?q={}'.format(kw)  # 构建含关键词的url
        try:
            source = self.download(query, timeout=10)
            # source = self.download(query,timeout=10,user_agent=self.ua)
            if source:
                kw_list = self.extract(source)
                print(kw_list)
                self.filter(cloop, kw_list)
            else:
                # 获取源码失败，保存查询失败的关键词
                self.failed.write('{}\n'.format(kw))
        finally:
            self.kw_queue.task_done()



def download(self, url, timeout=5, proxy=None, num_retries=5):
    """
    通用网页源码下载函数
    :param url: 要下载的url
    :param timeout: 请求超时时间，单位/秒。可能某些网站的反应速度很慢，所以需要一个连接超时变量来处理。
    :param user_agent: 用户代理信息，可以自定义是爬虫还是模拟用户
    :param proxy: ip代理(http代理)，访问某些国外网站的时候需要用到。必须是双元素元组或列表（‘ip：端口’，‘http/https’）
    :param num_retries: 失败重试次数
    :return: HTML网页源码
    """
    headers = {
        "Cookie": "QiHooGUID=41F80B0CCE5D43A22EEF0305A12CDE3F.1596003342506; __guid=15484592.2994995584481314300.1596003341831.5723; soid=TjzBKt3zrO-Rh1S7fXSb0S!6kmX5TlEerB2URZz9v4; __md=667cb161f9515972323507763d8fa7dd643a65bd2e88034.9; dpr=1; isafe=1; webp=1; _uc_m2=886a48052dbb9e2291f80055746e0d4f1f110f922b2f; _uc_mid=7cb161f953d8fa7dd643a65bd2e88034; __huid=11xZqhEl%2FfVeqclI4j%2BdQeQvX63Oph%2F%2BCVM5vxqYGxQI4%3D; Q=u%3Duhthb002%26n%3D%26le%3DAwH0ZGV5ZGR3WGDjpKRhL29g%26m%3DZGH5WGWOWGWOWGWOWGWOWGWOZGL0%26qid%3D144048053%26im%3D1_t018c25fbb66797efb2%26src%3D360chrome%26t%3D1; T=s%3D2afa764886f737dd5d23421c30f87a1f%26t%3D1595934758%26lm%3D0-1%26lf%3D2%26sk%3De485bbde46ac34fc27fc40215de76c44%26mt%3D1595934758%26rc%3D1%26v%3D2.0%26a%3D1; _S=tg75a7e3fmv0mfdfkt8jlpfpj6; stc_ls_sohome=RRzRSR!RTR(RUR_RVR; gtHuid=1; homeopenad=1; _pp_wd=1; _ga=GA1.2.607533084.1598082638; _gid=GA1.2.1887117715.1598082638; count=6; erules=p1-9%7Cp2-11%7Cp4-3%7Cecl-2%7Ckd-1%7Cp3-2",
        'User-Agent': random.choice(self.ua_list)
    }
    try:
        # 打开网页并读取内容存入html变量中
        resp = requests.get(url, headers=headers, proxies=proxy, timeout=timeout)
        print(resp.status_code)
    except requests.RequestException as err:
        print('Download error:', err)
        html = None  # 如果有异常，那么html肯定是没获取到的，所以赋值None
        if num_retries > 0:
            return self.download(url, timeout, proxy, num_retries - 1)
    else:
        html = resp.content.decode('utf-8')
        #print(html)
    return html


@staticmethod
def extract(html):
    '''
    提取关键词
    :param html:搜索结果源码
    :return:提取出来的相关关键词列表

    '''

    return re.findall(r'<a data-ext=".+?" href=".+?">(.+?)</a>', html, re.S | re.I)




def filter(self, current_loop, kwlist):
    '''
    关键词过滤和统计函数
    :param current_loop: 当前拓展的次数
    :param kwlist: 提取出来的关键词列表
    :return: None
    '''
    for kw in kwlist:
        # 判断关键词是不是已经被抓取或者已经存在关键词队列
        # 判断当前的拓展次数是否已经超过指定值
        if current_loop < self.loop and kw not in self.seen:
            # 同时满足关键词的拓展次数小于目标次数，而且关键词不在seen里面时才把kw放到待抓取队列内
            self.kw_queue.put((kw, current_loop+1))
            Qh360Spider.seen.add(kw)
        # 将关键词放到结果字典内，并统计出现次数
        if kw in self.result:
            Qh360Spider.result[kw] += 1
        else:
            Qh360Spider.result[kw] = 1

if name == 'main':

# 创建关键词队列实例

k_queue = Queue()

# 将待抓取关键词放入队列已经类的seen属性中

with open('keywords.txt', encoding="GBK") as kwfile:

for key in kwfile:

key = key.strip()

k_queue.put((key, 1))

Qh360Spider.seen.add(key)
# 创建查询失败保存文件
check_failed = open('faileds.txt', 'w')
# 创建线程
for i in range(15):
    bds = Qh360Spider(k_queue, 3, check_failed)
    bds.setDaemon(True)
    bds.start()
# 阻塞关键词队列，直到完成
k_queue.join()
# 关闭查询失败的文件
check_failed.close()

# 对结果进行排序及写入文件
sort_list = sorted(Qh360Spider.result.items(), key=lambda x: x[1], reverse=True)
with open('ah360key.txt', 'w', encoding='utf8') as save:
    for item in sort_list:
        # 关键词+次数的文件输出方式
        line = '%s\n' % (item[0])
        if len(line) > 0:
            print("有东西")
        print('111')
        save.write(line)
        save.flush()  # 刷新缓存，避免中途出错
    save.close()
print('done，完成挖掘')