Python与Seo工具源码，全网搜录查询助手exe
Python与Seo工具源码，全网搜录查询助手exe
很多人都说，seo是一个玄学，诚然，一方面是排名，另一方面是收录，尤其是对于渣渣而言，当然收录和排名都需要去验证，去查询，乃至去监控，大批量的话，你得自己去用工具去完成，能参与排名的前提是需要收录，所以关注搜录数据是必备的！
seo助手工具，全网搜录查询助手exe，应用python编写，可以实现批量导入要查询的网址，能实现的搜索引擎为：百度，搜狗以及360搜索引擎，导出网址已经分开为未收录文本文档（fail）以及已收录文本文档（succ），low比版，开了四个线程，差不多够用吧，工具和谐程度未知，等着你试用分享！
估计大佬们都看不上，看着玩吧！
对了，谨慎下载，需要关注本渣渣公众号，直接回复“搜录查询”，获取授权运行码，介意勿下！
链接: https://pan.baidu.com/s/1thNfN1ZVzXs01NipBel6CQ
提取码: s25b
当然，这里源码已经附上，可自行修改和调试！
有问题也可以加本渣渣微信交流探讨！
导入查询网址
导入查询网址，格式为txt，一行一个网址
#导入查询网址
class Get_urls():
def __init__(self):
self.search_urls=[]
def get_txt_urls(self,txt_path):
print('>> 正在尝试导入文本数据..')
try:
with open(txt_path,'r',encoding='gbk') as f:
txt_urls=f.readlines()
except:
print("该文档为 utf-8 编码格式！")
with open(txt_path,'r',encoding='utf-8') as f:
txt_urls=f.readlines()
print(f'>> 共有{len(txt_urls)}条初始数据！')
for url in txt_urls:
url=url.split()[0]
if "锘縣ttps" in url:
url=url.replace("锘縣ttp","http")
self.search_urls.append(url)
print(self.search_urls)
return self.search_urls
百度搜录查询
百度搜录查询，验证关键词："没有找到"
#百度搜录查询
class B_search():
def __init__(self):
self.ua=UserAgent()
self.join_urls=[]
self.results=[]
self.headers={
"User-Agent":self.ua.random,
"Cookie": "BIDUPSID=A461AAF74635FFC7C8F38B6A59BA8BF5; PSTM=1595934808; H_WISE_SIDS=148077_150112_150830_153110_149355_149986_150076_147089_150087_151863_148867_150745_147279_152309_150647_153106_152537_151533_151015_151558_152590_148523_151032_127969_153226_146548_152505_152902_146652_151319_146732_153059_152740_150764_131423_152018_151389_149009_107319_151182_149251_153181_152284_144966_153116_152269_152514_152739_152249_149773_148868_150113_151703_110085; BAIDUID=0671E35F80D2F5FEEDB8387648940553:FG=1; MCITY=-%3A; BD_UPN=12314353; sug=3; ORIGIN=0; bdime=0; sugstore=1; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; delPer=0; BD_CK_SAM=1; PSINO=6; sajssdk_2015_cross_new_user=1; sensorsdata2015jssdkcross=%7B%22distinct_id%22%3A%2219306004%3A0%22%2C%22first_id%22%3A%2217587fc96ba21d-04c73361861a03-4e4c0f20-2073600-17587fc96bb59d%22%2C%22props%22%3A%7B%22%24latest_traffic_source_type%22%3A%22%E7%9B%B4%E6%8E%A5%E6%B5%81%E9%87%8F%22%2C%22%24latest_search_keyword%22%3A%22%E6%9C%AA%E5%8F%96%E5%88%B0%E5%80%BC_%E7%9B%B4%E6%8E%A5%E6%89%93%E5%BC%80%22%2C%22%24latest_referrer%22%3A%22%22%7D%2C%22%24device_id%22%3A%2217587fc96ba21d-04c73361861a03-4e4c0f20-2073600-17587fc96bb59d%22%7D; COOKIE_SESSION=2015_0_6_6_8_12_0_2_6_3_0_0_1952_0_0_0_1604300209_0_1604302136%7C9%23109815_15_1604053694%7C9; H_PS_PSSID=32820_1468_32874_32950_31660_32971_32723_7517_32117_32761; H_PS_645EC=b52c4oJuV08TA0pmH4qjMkzfvHBbPk1qT7MqNhHISWgWQcT%2BoTNGjSbPDbc; BA_HECTOR=0l8ga00h8k20843jt31fpvigt0o",
}
def bjoinurls(self,search_urls):
for search_url in search_urls:
join_url=f'https://www.baidu.com/s?wd={search_url}'
self.join_urls.append(join_url)
print(self.join_urls)
return self.join_urls
#单线程
def bdsearch(self,url):
print(f'>> 正在查询 {url} 百度是否收录..')
response=requests.get(url,headers=self.headers,timeout=5)
time.sleep(2)
if response.status_code ==200:
html=response.content.decode('utf-8')
result_url = url.split("wd=")[1]
#print(html)
if "没有找到" in html:
print(f"{result_url} -百度未收录")
self.results.append(f"{result_url} -百度未收录")
with open('fail_baidu.txt','a+',encoding='utf-8') as f:
f.write(f"{result_url}\n")
else:
print(f"{result_url} -百度已收录")
self.results.append(f"{result_url} -百度已收录")
with open('succ_baidu.txt','a+',encoding='utf-8') as f:
f.write(f"{result_url}\n")
#多线程
def dxc_bdsearch(self,urls):
print(f'>> 正在开启多线程查询..')
try:
# 开4个 worker，没有参数时默认是 cpu 的核心数
pool = ThreadPool()
results = pool.map(self.bdsearch, urls)
pool.close()
pool.join()
print("百度搜录查询已完成！")
except:
print("Error: unable to start thread")
return self.results
搜狗搜录查询
搜狗搜录查询，大同小异，验证关键词："0条相关"
#搜狗收录查询
class Sg_search():
def __init__(self):
self.ua = UserAgent()
self.join_urls = []
self.results = []
self.headers = {
"User-Agent": self.ua.random,
"Cookie": "IPLOC=CN4403; SUID=981D0EB73220910A000000005F2131A2; SUV=00972C5AB70E1D985F2131A3FD344494; _ga=GA1.2.1265874139.1596180079; CXID=E8A7C57E2DACC58DC6FC681AFAE3E866; ssuid=7879419577; sw_uuid=7947207841; pgv_pvi=1464691712; wuid=AAFxJvHlMAAAAAqLMVQSlQQAGwY=; ABTEST=8|1601979367|v17; ad=Ylllllllll2KJv@4lllllVMzgV7lllllHZfptkllllGlllll4qxlw@@@@@@@@@@@; SNUID=E87FF74FF8FD4A166C307EB8F944606F; browerV=3; osV=1; ld=yZllllllll2KXDLVlllllVMK8YUlllllHZfpTlllll9llllllklll5@@@@@@@@@@; sst0=880",
}
def sgjoinurls(self, search_urls):
for search_url in search_urls:
join_url = f'https://www.sogou.com/web?query={search_url}'
self.join_urls.append(join_url)
print(self.join_urls)
return self.join_urls
# 单线程
def sgsearch(self, url):
print(f'>> 正在查询 {url} 搜狗是否收录..')
response = requests.get(url, headers=self.headers, timeout=5)
time.sleep(2)
if response.status_code == 200:
html = response.content.decode('utf-8')
result_url = url.split("query=")[1]
# print(html)
if "0条相关" in html:
print(f"{result_url} -搜狗未收录")
self.results.append(f"{result_url} -搜狗未收录")
with open('fail_sougou.txt','a+',encoding='utf-8') as f:
f.write(f"{result_url}\n")
else:
print(f"{result_url} -搜狗已收录")
self.results.append(f"{result_url} -搜狗已收录")
with open('succ_sougou.txt','a+',encoding='utf-8') as f:
f.write(f"{result_url}\n")
# 多线程
def dxc_sgsearch(self, urls):
print(f'>> 正在开启多线程查询..')
try:
# 开4个 worker，没有参数时默认是 cpu 的核心数
pool = ThreadPool()
results = pool.map(self.sgsearch, urls)
pool.close()
pool.join()
print("搜狗搜录查询已完成！")
except:
print("Error: unable to start thread")
return self.results
这里提一个醒，http和https搜录查询结果是不一样的，百思不得其解！！
360搜录查询
搜狗搜录查询，大同小异，验证关键词："0条相关"
#360收录查询
class S360_search():
def __init__(self):
self.ua = UserAgent()
self.join_urls = []
self.results=[]
self.headers = {
"User-Agent": self.ua.random,
"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; _ga=GA1.2.607533084.1598082638; so_md=307cb1159868390853561f953d8fa7dd643a65bd2e88034.4; so_huid=11xZqhEl%2FfVeqclI4j%2BdQeQvX63Oph%2F%2BCVM5vxqYGxQI4%3D; __guid=9114931.3673932918268830000.1601026204371.0352; __mid=7cb161f953d8fa7dd643a65bd2e88034; __gid=9114931.910562614.1601026204503.1603272604905.85; Q=u%3Duhthb002%26n%3D%26le%3DAwH0ZGV5ZGR3WGDjpKRhL29g%26m%3DZGH5WGWOWGWOWGWOWGWOWGWOZGL0%26qid%3D144048053%26im%3D1_t018c25fbb66797efb2%26src%3D360chrome%26t%3D1; T=s%3D9015aaf14e7f5a2899505e57f0923273%26t%3D1595934758%26lm%3D0-1%26lf%3D2%26sk%3Dd659153bc633959211cc6224482ba1d9%26mt%3D1595934758%26rc%3D3%26v%3D2.0%26a%3D1; _pp_wd=1; erules=p2-1%7Cp1-7%7Cecl-2%7Ckd-5; _S=lugbh23cn4guran76ieenpmj67; gtHuid=1; count=6",
}
def s360joinurls(self, search_urls):
for search_url in search_urls:
join_url = f'https://www.so.com/s?q={search_url}'
self.join_urls.append(join_url)
print(self.join_urls)
return self.join_urls
# 单线程
def s360search(self, url):
print(f'>> 正在查询 {url} 360是否收录..')
response = requests.get(url, headers=self.headers, timeout=5)
time.sleep(2)
if response.status_code == 200:
html = response.content.decode('utf-8')
result_url = url.split("q=")[1]
# print(html)
if "找不到" in html:
print(f"{result_url} -360未收录")
self.results.append(f"{result_url} -360未收录")
with open('fail_360.txt','a+',encoding='utf-8') as f:
f.write(f"{result_url}\n")
else:
print(f"{result_url} -360已收录")
self.results.append(f"{result_url} -360已收录")
with open('succ_360.txt','a+',encoding='utf-8') as f:
f.write(f"{result_url}\n")
# 多线程
def dxc_s360search(self, urls):
print(f'>> 正在开启多线程查询..')
try:
# 开4个 worker，没有参数时默认是 cpu 的核心数
pool = ThreadPool()
results = pool.map(self.s360search, urls)
pool.close()
pool.join()
print("360搜录查询已完成！")
except:
print("Error: unable to start thread")
return self.results
本文参与 腾讯云自媒体分享计划，分享自微信公众号。
原始发表：2020-11-03，如有侵权请联系 cloudcommunity@tencent.com 删除
评论
登录后参与评论
推荐阅读
目录