python测试6_python自动化测试_6

目录

接口测试编码:

url编码：

from urllib import parse

url = 'http://zzk.cnblogs.com/s/blogpost?Keywords=中文'

a = '中文'

b = parse.quote(a) # 转urlencode编码

print(b)

print(parse.quote(b)) # 转第二次(若有需求)

解码：

c = '%E4%B8%AD%E6%96%87'

d = parse.unquote(c)

print(d)

f = 'http://zzk.cnblogs.com/s/blogpost?Keywords=%E4%B8%AD%E6%96%87'

print(parse.unquote(f))

密码登录：

问题：

1.每次密码都是转变的，无法通过账号密码登录

2. 登录有验证码怎么办？

3.不想看到浏览器启动怎么办？

解决思绪：

1.先用selenium挪用浏览器(不会selenium的自己想办法了)，

2.登录后从浏览器内里抓取cookies

3.把cookies传给s

4.这样就乐成乐成了

登录有验证码怎么办？

参考这篇：http://www.cnblogs.com/yoyoketang/p/8610779.html

每次都市启动浏览器界面，不想看到浏览器启动怎么办？

解决办法1：用chrome的headless模式 http://www.cnblogs.com/yoyoketang/p/8078873.html

案例：

chromedriver.exe需要加到环境变量path

from selenium import webdriver

option = webdriver.ChromeOptions()

option.add_argument('headless') # 静默模式 [后台运行]

# 打开chrome浏览器

driver = webdriver.Chrome( chrome_options=option)

driver.get("https://www.cnblogs.com/yoyoketang")

print(driver.title)

import requests

from selenium import webdriver

from bs4 import BeautifulSoup

import re

import time

# firefox浏览器设置文件地址

profile_directory = r'C:\Users\admin\AppData\Roaming\Mozilla\Firefox\Profiles\yn80ouvt.default'

s = requests.session() # 新建session

url = "https://home.cnblogs.com/u/yoyoketang"

def get_cookies(url):

'''启动selenium获取登录的cookies'''

try:

# 加载设置

profile = webdriver.FirefoxProfile(profile_directory)

# 启动浏览器设置

driver = webdriver.Firefox(profile)

driver.get(url+"/followers")

time.sleep(3)

cookies = driver.get_cookies() # 获取浏览器cookies

print(cookies)

driver.quit()

return cookies

except Exception as msg:

print(u"启动浏览器报错了：%s" %str(msg))

def add_cookies(cookies):

'''往session添加cookies'''

try:

# 添加cookies到CookieJar

c = requests.cookies.RequestsCookieJar()

for i in cookies:

c.set(i["name"], i['value'])

s.cookies.update(c) # 更新session里cookies

except Exception as msg:

print(u"添加cookies的时刻报错了：%s" % str(msg))

def get_ye_nub(url):

'''获取粉丝的页面数目'''

try:

# 发请求

r1 = s.get(url+"/relation/followers")

soup = BeautifulSoup(r1.content, "html.parser")

# 抓取我的粉丝数

fensinub = soup.find_all(class_="current_nav")

print(fensinub[0].string)

num = re.findall(u"我的粉丝\((.+?)\)", fensinub[0].string)

print(u"我的粉丝数目：%s"%str(num[0]))

# 盘算有若干页，每页45条

ye = int(int(num[0])/45)+1

print(u"总共分页数：%s"%str(ye))

return ye

except Exception as msg:

print(u"获取粉丝页数报错了，默认返回数目1 ：%s"%str(msg))

return 1

def save_name(nub):

'''抓取页面的粉丝名称'''

try:

# 抓取第一页的数据

if nub <= 1:

url_page = url+"/relation/followers"

else:

url_page = url+"/relation/followers?page=%s" % str(nub)

print(u"正在抓取的页面：%s" %url_page)

r2 = s.get(url_page, verify=False)

soup = BeautifulSoup(r2.content, "html.parser")

fensi = soup.find_all(class_="avatar_name")

for i in fensi:

name = i.string.replace("\n", "").replace(" ","")

print(name)

with open("name.txt", "a") as f: # 追加写入

f.write(name.encode("utf-8")+"\n")

# python3的改成下面这两行

# with open("name.txt", "a", encoding="utf-8") as f: # 追加写入

# f.write(name+"\n")

except Exception as msg:

print(u"抓取粉丝名称历程中报错了 ：%s"%str(msg))

if __name__ == "__main__":

cookies = get_cookies(url)

add_cookies(cookies)

n = get_ye_nub(url)

for i in list(range(1, n+1)):

save_name(i)

原文链接：https://www.cnblogs.com/shaozheng/p/12874146.html

本站声明:网站内容来源于网络,若有侵权,请联系我们,我们将及时处理。