您的位置:

python注册大量用户,python多用户登录

本文目录一览:

python怎么在Linux实现创建用户?

题主你好,

我以创建user1-user10个用户为例, 代码为测试截图如下:

1. 系统中不存在user1-user10:

执行脚本:

可以看到脚本执行后, 显示成功添加用户数10个, 失败0个.并且/etc/shadow中相应的用户信息也有了.

-------------

我们删掉user0, user1和user2:

可以看到/etc/shadow中的信息已经没有了user0-user2的信息了,此时我们再执行上面的脚本:

可以看到输出显示, 成功创建3个,就是我们之前删掉的那三个. 还有7个创建失败的, 因为用户本身就存在所以创建失败了.

希望可以帮到题主, 欢迎追问.

python设计函数,实现会员注册,要求用户名长度不小于3,密码长度不小于6, 注册时两次输入密码必须相同

def log_in():

username=input("输入用户名(不小于3位)")

if len(username)=3:

password=input("密码(不小于六位)")

if len(password)=6:

pass_1=input("再次输入密码")

if password==pass_1:

print("注册成功")

else:

print("两次输入密码不一致")

log_in()

else:

print("密码长度不符合要求")

log_in()

else:

print("帐号长度不符合要求")

log_in()

log_in()

python注册程序编写?

import

re

username_pattern

=

re.compile(r'_.{2,29}')

password_pattern

=

re.compile(r'(?=.*_)(?=.*\d)(?=.*[A-Za-z]).{6,18}')

然后用相应的pattern,去match用户输入的字符串即可。

python批量注册账号 数据库会崩溃吗

不会的,一般不会同时运行太多账号,数据库可支撑力是很大的,不用担心这个问题,要批量注册所需要用的代码如下:

# -*- coding:utf-8 -*-

import random,urllib,urllib2

import re,time

x=input("请输入需要注册的数量:")

# x=raw_input() #转换成字符串的

def h(i,y):

   user=str(random.randrange(10000000,99999999))

QQ=str(random.randrange(10001,999999999999))

  pwd=str(random.randrange(100000,99999999))

  url=""

  data={"username":user,

  "password":pwd,

  "repassword":pwd,

  "email":QQ+"@qq.com",

  "qq":QQ,

  "sex":"0",

  "action":"newuser",

  "submit":""}

  data=urllib.urlencode(data)

  req=urllib2.Request(url,data=data)

  print data

  # html=urllib2.urlopen(req).read()

  # print(html)

  html=urllib2.urlopen(req).read().decode('gbk')

  # print(type(html))

  reg=u'您已成功注册成为本站用户'

  reg=re.compile(reg)

  r=re.findall(reg,html)

  if r!=[]:

      print("注册成功,账号为%s,密码为%s,目前注册到第%s,还剩%s个"%(user,pwd,i+1,y-i-1))

      f=open("c:\user.txt","a")

      f.write("%s----%s----%s@qq.com----%s\n" %(user,pwd,QQ,QQ))

      # f.write("qq----123456")

      f.close()

for i in range(x):

  h(i,x)

  # 延时

  time.sleep(2)

python怎么爬取简书用户名

初步的思路

今天在用Scrapy写代码的时候,对网页的结构也有了大致的分析,再加上之前罗罗攀的思路,初步我是通过专题入口

热门专题

image.png

image.png

专题管理员 (一般粉丝、文章、字数、收获喜欢、这几项数据都非常漂亮)

image.png

image.png

以上红框里的数据项就是我需要爬取的字段

但是以上的思路存在一点的问题:

存在一些简书用户并不是一些热门专题的管理员,但是其人气粉丝量也很高,这个思路可能无法将这些用户爬取下来

进阶的思路

热门专题

专题关注的人

专题关注的人的动态

推荐作者 粉丝信息

image.png

image.png

image.png

优点:

数据大而全,基本包含了99%的用户(个人猜测,不严谨)

缺点:

因为许多用户不止关注一个专题,而且其中包含了大量的新注册用户(数据很多为空),并且也有大量重复数据需要去重

代码部分:

jianshu.py 还在调试阶段,待更新...

# -*- coding: utf-8 -*-

import sys

import json

import requests

import scrapy

import re

from lxml import etree

from scrapy.http import Request

reload(sys)

sys.path.append('..')

sys.setdefaultencoding('utf-8')

class jianshu(scrapy.Spider):

name = 'jianshu'

# topic_category = ['city']

topic_category = ['recommend', 'hot', 'city']

base_url = 'lections?page=%sorder_by=%s'

cookies={

'UM_distinctid': '15b89d53a930-02ab95f11ccae2-51462d15-1aeaa0-15b89d53a9489b',

'CNZZDATA1258679142': '1544557204-1492664886-%7C1493280769',

'_session_id': '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%3D%3D--0849c37208f8c573960d857029c7d6a15145c419',

'remember_user_token':'W1szNDgxMjU3XSwiJDJhJDEwJDlSS3VLcFFWMlZzNFJuOFFNS1JQR3UiLCIxNDk0MjEzNDQ3LjYwODEwNzgiXQ%3D%3D--9241542a4e44d55acaf8736a1d57dd0e96ad4e7a',

'_ga': 'GA1.2.2016948485.1492666105',

'_gid': 'GA1.2.382495.1494550475',

'Hm_lpvt_0c0e9d9b1e7d617b3e6842e85b9fb068': '1494550475',

'Hm_lvt_0c0e9d9b1e7d617b3e6842e85b9fb068': '1494213432,1494213612,1494321303,1494387194'

}

headers = {

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

'Accept - Language': 'zh - CN, zh;q = 0.8',

'Connection': 'close',

'Cookie': 'UM_distinctid=15b89d53a930-02ab95f11ccae2-51462d15-1aeaa0-15b89d53a9489b; CNZZDATA1258679142=1544557204-1492664886-%7C1493280769; remember_user_token=W1szNDgxMjU3XSwiJDJhJDEwJDlSS3VLcFFWMlZzNFJuOFFNS1JQR3UiLCIxNDk0MjEzNDQ3LjYwODEwNzgiXQ%3D%3D--9241542a4e44d55acaf8736a1d57dd0e96ad4e7a; _ga=GA1.2.2016948485.1492666105; _gid=GA1.2.824702661.1494486429; _gat=1; Hm_lvt_0c0e9d9b1e7d617b3e6842e85b9fb068=1494213432,1494213612,1494321303,1494387194; Hm_lpvt_0c0e9d9b1e7d617b3e6842e85b9fb068=1494486429; _session_id=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%3D%3D--ea401e8c501e7b749d593e1627dbaa88ab4befc2',

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.81 Safari/537.36',

'Host':'',

"X-Requested-With": 'XMLHttpRequest'

}

def get_total_page(self):

#获取专题总页数 包含3个字典的列表 [{"hot": xx}, {"recommend":xx}, {"city": xx}]

total_page_list = []

for order in self.topic_category:

order = order.decode('utf-8')

total_page = 100

dict = {}

for page in range(1, total_page):

url = self.base_url % (page, order)

html = requests.get(url, headers=self.headers).content

selector = etree.HTML(html)

#print html

try:

elements = selector.xpath('//*[@id="list-container"]/div[1]/div/h4/a/text()')[0]

if elements is not Exception:

continue

except Exception :

dict['total_page'] = page - 1

dict['category'] = order

break

total_page_list.append(dict)

return total_page_list

def get_topic_info(self):

#获取专题信息

topic_info_list = []

total_page_list = self.get_total_page()

base_url = self.base_url

for dict in total_page_list:

category = dict['category']

total_page = int(dict['total_page'])

for page in range(1, total_page + 1):

url = base_url % (page, category)

html = requests.get(url, headers=self.headers,cookies=self.cookies).content

selector = etree.HTML(html)

topic_href = selector.xpath('//*[@id="list-container"]')[0]

for href in topic_href:

dict = {}

topic_name = href.xpath('./div/h4/a/text()')[0]

topic_url = "" + href.xpath('./div/h4/a/@href')[0]

topic_img_url = href.xpath('./div/a/img/@src')[0]

img_num = topic_img_url.split("/")[5]

dict['topic_name'] = topic_name

dict['topic_url'] = topic_url

#

dict['img_num'] = img_num

topic_info_list.append(dict)

return topic_info_list

def get_topic_admin_info(self):

#获取管理员信息

topic_admin_info_list = []

topic_info_list = self.get_topic_info()

for d in topic_info_list:

img_num = str(d['img_num'])

base_url = "s/editors_and_subscribers" % img_num

base_url_response = requests.get(base_url, headers=self.headers, cookies=self.cookies)

json_data_base = json.loads(base_url_response.text.decode('utf-8'))

editors_total_pages = json_data_base['editors_total_pages']

for page in range(1, int(editors_total_pages) + 1):

if page == 1:

editors = json_data_base['editors']

for editor in editors:

dict = {}

dict['nickname'] = editor['nickname']

dict['slug'] = editor['slug']

topic_admin_info_list.append(dict)

else:

try:

url = "}/editors?page={}".format(img_num, page)

response = requests.get(url,headers=self.headers,cookies=self.cookies)

json_data = json.loads(response.text.decode('utf-8'))

editors = json_data['editors']

for editor in editors:

dict = {}

dict['nickname'] = editor['nickname']

dict['slug'] = editor['slug']

topic_admin_info_list.append(dict)

except Exception:

pass

return topic_admin_info_list

def get_followers_following_list(self):

# 获取管理员粉丝列表

followers_list = []

topic_admin_list = self.get_topic_admin_info()

followers_base_url = "s/%s/followers"

for dict in topic_admin_list:

url = followers_base_url % dict['slug']

headers = self.headers

headers['Referer'] = url

headers['DNT'] = '1'

response = requests.get(url, headers=headers, cookies=self.cookies).content

total_followers = re.fi