2019/6/17
今日内容：
1.requests之POST请求
2.requests高级用法
3.selenium模块
4.万能破解登录
上节课作业正确内容
# 电影详情页url、图片链接、电影名称、导演、主演、电影上映时间、电影评分、评价人数、简介
<div class="item">.*?href="(.*?)">.*?src="(.*?)" class="">.*?<span class="title">(.*?)</span>.*?<div class="bd">.*?导演:(.*?)<br>(.*?)</p>.*?<span class="rating_num".*?>(.*?)</span>.*?<span>(.*?)人评价.*?<span class="inq">(.*?)</span>
base_url = 'https://movie.douban.com/top250?start = {}&filter = '
n = 0
for line in range (10) :
print ()
ur; = base_url.format(n)
print (type(n))
n+=25
print(url)
#1、往豆瓣TOP250发送请求获取响应数据
response = requests.get(url.headers = headers)
#解压复制每一部电影
detail_url,movie_jpg,name,daoyan,timer,point,num,desc = movie_content
data = f'电影名称：{name}, 详情页url:{detail_url},图片url：{movie_jpg}'
导演： {daoyan} 上映时间：{timer} 评分：{point}， 评分人数：{num 简介：{desc}、n'
print(data)
请求URL
http://gitbub.com/sossion
联系方式：
POST
请求头：
Rofeier: http://github.com/login
User-Agent:mozilla/5.0 (window NT 10.0: wow64) Applowobkit?
请求体：
只有POST请求才会有请求体
commit: sign in
utf8:
autbenticiy_token: vx79esfcosfdgs/sdfsfsfgsfg/sfs
login: tank.jaml
password:kemit32423424
webauthn-support:unsuported
' ' '
请求url
https://githuh.con/login
请求方式：
GET
响应头：
Set-Cookie
请求头：
cookie
user-agent
' ' '
headers = {
'user-agent':,'mozilla/5.0(windows nt 10.0: wow64) applewebkit/535.36(khtml,)}
response = requests.get(url = 'https: //github.com/login', headers=headers)
#print(response.text)
authenticity_token = re.findall('<input type = "hidden" name = "authenaticity_token" value = "(.*?)"/>'),response.text, re.s) [0]
print(authenticity_token)
''' #访问login页获取token信息
''' 请求URL：
token=re.findall('zhengzeguize',response.tex,re.S)[0] print(token) #找到第一个页面的token
#登录 往session发送post请求 #请求的URL=
import requests
r = requests.get('https://api.github.com/events')
r = requests.post('http://httpbin.org/post', data = {'key':'value'})
r = requests.put('http://httpbin.org/put', data = {'key':'value'})
r = requests.delete('http://httpbin.org/delete')
r = requests.head('http://httpbin.org/get')
r = requests.options('http://httpbin.org/get')
from urllib.parse import urlencode import requests
# q后面携带的是中文墨菲定律 response1 = requests.get('https://list.tmall.com/search_product.htm?q=%C4%AB%B7%C6%B6%A8%C2%C9') print(response1.text)
# 因为字符编码的问题，以至于中文变成了一些特殊的字符，所以我们要找到一种解决方案 url = 'https://list.tmall.com/search_product.htm?' + urlencode({'q': '墨菲定律'}) response2 = requests.get(url) print(response2.text)
# get方法为我们提供了一个参数params，它内部其实就是urlencode response3 = requests.get('https://list.tmall.com/search_product.htm?', params={"q": "墨菲定律"}) print(response3.text)
import requests
headers = { 'User-Agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.76 Mobile Safari/537.36', }
response = requests.get('https://www.github.com', headers=headers)
# response响应 print(response.status_code)
# 获取响应状态码 print(response.url)
# 获取url地址 print(response.text)
# 获取文本 print(response.content)
# 获取二进制流 print(response.headers)
# 获取页面请求头信息 print(response.history)
# 上一次跳转的地址 print(response.cookies)
# # 获取cookies信息 print(response.cookies.get_dict())
# 获取cookies信息转换成字典 print(response.cookies.items())
# 获取cookies信息转换成字典 print(response.encoding)
# 字符编码 print(response.elapsed)
# 访问时间
import requests
headers = { 'User-Agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.76 Mobile Safari/537.36', }
# 编码问题 response = requests.get('http://www.autohome.com/news', headers=headers) # print(response.text)
# 汽车之家网站返回的页面内容编码为gb2312，而requests的默认编码为ISO-8859-1，如果不设置成gbk则中文乱码 response.encoding = 'gbk' print(response.text)
import requests
#往音频地址发送get请求
url = 'http://vd3.badstatic.com/mda-ic4pfhh32svqi/hd/mda-ic4pfhh3eh3ex32svqi.mp4?auth_key = 123123452345444dsfvjfsngswrut834u rgwrghrgububbn'
resp[onse = requests.get(url, stream = True)
#stream = True 把content设置为一个迭代器对象
print (response.content)
with open('love_for_GD.mp4','wb') as f :
for content in response.iter_content():
f.write(content)
# 代理设置:先发送请求给代理,然后由代理帮忙发送(封ip是常见的事情)
import requests proxies={
# 带用户名密码的代理,@符号前是用户名与密码
'http':'http://tank:123@localhost:9527',
'http':'http://localhost:9527',
'https':'https://localhost:9527', } response=requests.get('https://www.12306.cn',
proxies=proxies)
print(response.status_code)
# 支持socks代理,安装:pip install requests[socks] import requests proxies = {
'http': 'socks5://user:pass@host:port',
'https': 'socks5://user:pass@host:port' } respone=requests.get('https://www.12306.cn',
proxies=proxies)
print(respone.status_code)
# from selenium import webdriver # 用来驱动浏览器的 # import time # # ''' # 隐式等待 # ''' # # 获取驱动对象、 # driver = webdriver.Chrome() # # try: # # 显式等待: 等待某个元素加载 # # 参数1: 驱动对象 参数2: 等待时间 # # wait = WebDriverWait(chrome, 10) # # driver.get('https://china.nba.com/') # # # 隐式等待: 等待页面所有元素加载 # driver.implicitly_wait(10) # news_tag = driver.find_element_by_class_name('nav-news') # # 获取标签对象 # print(news_tag) # # 获取标签的名字 # print(news_tag.tag_name) # # # time.sleep(10) # # finally: # driver.close() from selenium import webdriver # 用来驱动浏览器的 import time
''' ===============所有方法=================== element是查找一个标签 elements是查找所有标签 1、find_element_by_link_text 通过链接文本去找 2、find_element_by_id 通过id去找 3、find_element_by_class_name 4、find_element_by_partial_link_text 5、find_element_by_name 6、find_element_by_css_selector 7、find_element_by_tag_name ''' # 获取驱动对象、 driver = webdriver.Chrome()
try:
# 往百度发送请求 driver.get('https://www.baidu.com/') driver.implicitly_wait(10)
# 1、find_element_by_link_text 通过链接文本去找 # 根据登录 # send_tag = driver.find_element_by_link_text('登录') # send_tag.click() # 2、find_element_by_partial_link_text 通过局部文本查找a标签 login_button = driver.find_element_by_partial_link_text('登') login_button.click() time.sleep(1)
# 3、find_element_by_class_name 根据class属性名查找 login_tag = driver.find_element_by_class_name('tang-pass-footerBarULogin') login_tag.click() time.sleep(1)
# 4、find_element_by_name 根据name属性查找 username = driver.find_element_by_name('userName') username.send_keys('15622792660') time.sleep(1)
# 5、find_element_by_id 通过id属性名查找 password = driver.find_element_by_id('TANGRAM__PSP_10__password') password.send_keys('*******') time.sleep(1)
# 6、find_element_by_css_selector 根据属性选择器查找 # 根据id查找登录按钮 login_submit = driver.find_element_by_css_selector('#TANGRAM__PSP_10__submit') # driver.find_element_by_css_selector('.pass-button-submit') login_submit.click()
# 7、find_element_by_tag_name 根据标签名称查找标签 div = driver.find_element_by_tag_name('div') print(div.tag_name)
time.sleep(10)
finally: driver.close()
''' ''' ''' 证书验证(大部分网站都是https) ''' import requests # # 如果是ssl请求,首先检查证书是否合法,不合法则报错,程序终端 # response = requests.get('https://www.xiaohuar.com') # print(response.status_code) # 改进1:去掉报错,但是会报警告 # import requests # response = requests.get('https://www.xiaohuar.com', verify=False) # # 不验证证书,报警告,返回200 # print(response.status_code) # 改进2:去掉报错,并且去掉警报信息 # import requests # import urllib3 # urllib3.disable_warnings() # 关闭警告 # response = requests.get('https://www.xiaohuar.com', verify=False) # print(response.status_code) # 改进3:加上证书 # 很多网站都是https,但是不用证书也可以访问,大多数情况都是可以携带也可以不携带证书 # 知乎\百度等都是可带可不带 # 有硬性要求的,则必须带，比如对于定向的用户,拿到证书后才有权限访问某个特定网站 # import requests # import urllib3 # # urllib3.disable_warnings() # 关闭警告 # # 伪代码 # response = requests.get( # 'https://www.xiaohuar.com', # # verify=False, # # /path/server.crt证书的存放目录， /path/key # cert=('/path/server.crt', '/path/key')) # print(response.status_code) ''' 超时设置 ''' # 超时设置 # 两种超时:float or tuple # timeout=0.1 # 代表接收数据的超时时间 # timeout=(0.1,0.2) # 0.1代表链接超时 0.2代表接收数据的超时时间 # import requests # response = requests.get('https://www.baidu.com', # timeout=0.0001) # # print(response.elapsed) # print(response.status_code) ''' 代理设置:先发送请求给代理,然后由代理帮忙发送(封ip是常见的事情) ''' # import requests # proxies={ # # 带用户名密码的代理,@符号前是用户名与密码 # 'http':'http://tank:123@localhost:9527', # 'http':'http://localhost:9527', # 'https':'https://localhost:9527', # } # response=requests.get('https://www.12306.cn', # proxies=proxies) # # print(response.status_code) ''' 爬取西刺免费代理： 1.访问西刺免费代理页面 2.通过re模块解析并提取所有代理 3.通过ip测试网站对爬取的代理进行测试 4.若test_ip函数抛出异常代表代理作废，否则代理有效 5.利用有效的代理进行代理测试 <tr class="odd"> <td class="country"><img src="//fs.xicidaili.com/images/flag/cn.png" alt="Cn"></td> <td>112.85.131.99</td> <td>9999</td> <td> <a href="/2019-05-09/jiangsu">江苏南通</a> </td> <td class="country">高匿</td> <td>HTTPS</td> <td class="country"> <div title="0.144秒" class="bar"> <div class="bar_inner fast" style="width:88%"> </div> </div> </td> <td class="country"> <div title="0.028秒" class="bar"> <div class="bar_inner fast" style="width:97%"> </div> </div> </td> <td>6天</td> <td>19-05-16 11:20</td> </tr> re: <tr class="odd">(.*?)</td>.*?<td>(.*?)</td> ''' # import requests # import re # import time # # HEADERS = { # 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36', # } # # # def get_index(url): # time.sleep(1) # response = requests.get(url, headers=HEADERS) # return response # # # def parse_index(text): # ip_list = re.findall('<tr class="odd">.*?<td>(.*?)</td>.*?<td>(.*?)</td>', text, re.S) # for ip_port in ip_list: # ip = ':'.join(ip_port) # yield ip # # def test_ip(ip): # print('测试ip: %s' % ip) # try: # proxies = { # 'https': ip # } # # # ip测试网站 # ip_url = 'https://www.ipip.net/' # # # 使用有效与无效的代理对ip测试站点进行访问，若返回的结果为200则代表当前测试ip正常 # response = requests.get(ip_url, headers=HEADERS, proxies=proxies, timeout=1) # # if response.status_code == 200: # print(f'有用的ip：{ip}') # return ip # # # 若ip代理无效则抛出异常 # except Exception as e: # print(e) # # # 使用代理爬取nba # def spider_nba(good_ip): # url = 'https://china.nba.com/' # # proxies = { # 'https': good_ip # } # # response = requests.get(url, headers=HEADERS, proxies=proxies) # print(response.status_code) # print(response.text) # # # if __name__ == '__main__': # base_url = 'https://www.xicidaili.com/nn/{}' # # for line in range(1, 3677): # ip_url = base_url.format(line) # # response = get_index(ip_url) # # # 解析西刺代理获取每一个ip列表 # ip_list = parse_index(response.text) # # # 循环每一个ip # for ip in ip_list: # # print(ip) # # # 对爬取下来的ip进行测试 # good_ip = test_ip(ip) # # if good_ip: # # 真是代理，开始测试 # spider_nba(good_ip) ''' 认证设置 ''' import requests # 通过访问github的api来测试 url = 'https://api.github.com/user' HEADERS = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36', }
# 测试1，失败返回401 # response = requests.get(url, headers=HEADERS) # print(response.status_code) # 401 # print(response.text) ''' 打印结果: { "message": "Requires authentication", "documentation_url": "https://developer.github.com/v3/users/#get-the-authenticated-user" } ''' # # # 测试2，通过requests.auth内的HTTPBasicAuth进行认证，认证成功返回用户信息 # from requests.auth import HTTPBasicAuth # response = requests.get(url, headers=HEADERS, auth=HTTPBasicAuth('tankjam', 'kermit46709394')) # print(response.text) # # 测试3，通过requests.get请求内的auth参数默认就是HTTPBasicAuth，认证成功返回用户信息 # response = requests.get(url, headers=HEADERS, auth=('tankjam', 'kermit46709394')) # print(response.text) ''' 上传文件 ''' import requests
# 上传文本文件 # files1 = {'file': open('user.txt', 'rb')} # # files参数是POST请求固定参数 # response = requests.post('http://httpbin.org/post', files=files1) # print(response.status_code) # 200 # print(response.text) # 200 # 上传图片文件 # files2 = {'jpg': open('一拳.jpg', 'rb')} # response = requests.post('http://httpbin.org/post', files=files2) # print(response.status_code) # 200 # print(response.text) # 200 # # 上传视频文件 # files3 = {'movie': open('love_for_GD.mp4', 'rb')} # response = requests.post('http://httpbin.org/post', files=files3) # print(response.status_code) # 200 # print(response.text) # 200
今日作业：
1.整理课堂笔记并编写博客
2.爬取代理
（参考爬取西刺代理代码）
https://www.kuaidaili.com/free/
3.熟悉selenium模块，敲课上例子
4.自动登录抽屉新热榜
爬取快代理
'' 爬取快代理： 1.访问快代理页面 2.通过re模块解析并提取所有代理 3.通过ip测试网站对爬取的代理进行测试 4.若test_ip函数抛出异常代表代理作废，否则代理有效 5.利用有效的代理进行代理测试 <tr> <td data-title="IP">124.205.143.212</td> <td data-title="PORT">40585</td> <td data-title="匿名度">高匿名</td> <td data-title="类型">HTTP</td> <td data-title="位置">北京市北京市 鹏博士宽带</td> <td data-title="响应速度">2秒</td> <td data-title="最后验证时间">2019-06-17 16:30:54</td> </tr> re: <tr>.*?<td data-title="IP">(.*?)</td>.*?<td data-title="PORT">(.*?)</td> ''' ''' 页面链接 第一页： https://www.kuaidaili.com/free/ 第二页： https://www.kuaidaili.com/free/inha/2/ ''' import requests import re import time headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36', } def get_index(url): time.sleep(1) response1 = requests.get(url, headers=headers) return response1 def parse_index(text): ip_list1 = re.findall('<tr>.*?<td data-title="IP">(.*?)</td>.*?<td data-title="PORT">(.*?)</td>', text, re.S) for ip_port in ip_list1: ip1 = ':'.join(ip_port) yield ip1 def test_ip(ip2): print('测试ip: %s' % ip2) try: proxies = {'https': ip2} # ip测试网站 ip_url1 = 'https://www.ipip.net/' # 使用有效与无效的代理对ip测试站点进行访问，若返回的结果为200则代表当前测试ip正常 response2 = requests.get(ip_url1, headers=headers, proxies=proxies, timeout=1) if response2.status_code == 200: return ip # 若ip代理无效则抛出异常 except Exception as e: print(e) # 使用代理爬取nba def spider_nba(good_ip1): url = 'https://china.nba.com/' proxies = {'https': good_ip1} response3 = requests.get(url, headers=headers, proxies=proxies) print(response3.status_code) print(response3.text) if __name__ == '__main__': base_url = 'https://www.kuaidaili.com/free/inha/{}/' for line in range(1, 2905): ip_url = base_url.format(line) response = get_index(ip_url) ip_list = parse_index(response.text) for ip in ip_list: good_ip = test_ip(ip) if good_ip: spider_nba(good_ip)
自动登录抽屉新热榜
from selenium import webdriver import time #获取驱动对象 driver = webdriver.Chrome() try: #自动登陆抽屉新热榜 #发送get请求 driver.get('https://dig.chouti.com/ ') #隐式等待 driver.implicitly_wait(10) #获取 '登陆' 按钮 send_tag = driver.find_element_by_id('login_btn') send_tag.click() #获取手机号输入框 username = driver.find_element_by_class_name('login-phone') username.send_keys('***********') time.sleep(1) #获取密码输入框 password = driver.find_element_by_class_name('pwd-password-input') password.send_keys('***********') time.sleep(1) #获取 '登陆' 按钮 login = driver.find_elements_by_link_text('登录') login[1].click() time.sleep(10) finally: driver.close()
