#代理测试
import requests
from lxml import etree
import random
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'
}
#构建一个简易的ip池，字典形式的
proxy_list = [{'https':'212.64.51.13:8888'},{'https':'212.64.51.13:8888'},{'https':'212.64.51.13:8888'},
]
url = 'https://www.baidu.com/s?ie=UTF-8&wd=ip'
#proxies指定代理ip
page_text = requests.get(url=url,headers=headers,proxies=random.choice(proxy_list)).text
with open('ip.html','w',encoding='utf-8') as fp:fp.write(page_text)

import requests
from lxml import etree
import random
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'
}all_ips = []# 从代理精灵上买去的代理ip
ip_url = 'http://ip.11jsq.com/index.php/api/entry?method=proxyServer.generate_api_url&packid=1&fa=0&fetch_key=&groupid=0&qty=53&time=1&pro=&city=&port=1&format=html&ss=5&css=&dt=1&specialTxt=3&specialJson='
page_text = requests.get(ip_url,headers=headers).text
tree = etree.HTML(page_text)
ip_list = tree.xpath('//body//text()')# 取出所有的代理ip并组成列表
for ip in ip_list:ip = {'https':ip}all_ips.append(ip)url = 'https://www.xicidaili.com/nn/%d'
for page in range(1,100):print('正在爬取第{}页的数据！'.format(page))new_url = format(url%page)page_text = requests.get(url=new_url,headers=headers,proxies=random.choice(all_ips)).texttree = etree.HTML(page_text)tr_list = tree.xpath('//*[@id="ip_list"]//tr')[1:]for tr in tr_list:ip = tr.xpath('./td[2]/text()')[0]port = tr.xpath('./td[3]/text()')[0]ip_type = tr.xpath('./td[6]/text()')[0]dic = {'ip':ip,'port':port,'type':ip_type}all_ips.append(dic)print(len(all_ips))  

#通过抓包工具捕获的基于ajax请求的数据包中提取的url
url = 'https://xueqiu.com/v4/statuses/public_timeline_by_category.json?since_id=-1&max_id=20343389&count=15&category=-1'
json_data = requests.get(url=url,headers=headers).json()
print(json_data){'error_description': '遇到错误，请刷新页面或者重新登录帐号后再试', 'error_uri': '/v4/statuses/public_timeline_by_category.json', 'error_data': None, 'error_code': '400016'}

#创建一个session对象
session = requests.Session()
#将cookie保存到session对象中
first_url = 'https://xueqiu.com/'
session.get(url=first_url,headers=headers)#为了获取cookie且将cookie存储到session中

url = 'https://xueqiu.com/v4/statuses/public_timeline_by_category.json?since_id=-1&max_id=20343389&count=15&category=-1'
json_data = session.get(url=url,headers=headers).json()#携带cookie发起的请求
pprint(json_data)

import requests
from hashlib import md5class Chaojiying_Client(object):def __init__(self, username, password, soft_id):self.username = usernamepassword =  password.encode('utf8')self.password = md5(password).hexdigest()self.soft_id = soft_idself.base_params = {'user': self.username,'pass2': self.password,'softid': self.soft_id,}self.headers = {'Connection': 'Keep-Alive','User-Agent': 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)',}def PostPic(self, im, codetype):"""im: 图片字节codetype: 题目类型 参考 http://www.chaojiying.com/price.html"""params = {'codetype': codetype,}params.update(self.base_params)files = {'userfile': ('ccc.jpg', im)}r = requests.post('http://upload.chaojiying.net/Upload/Processing.php', data=params, files=files, headers=self.headers)return r.json()def ReportError(self, im_id):"""im_id:报错题目的图片ID"""params = {'id': im_id,}params.update(self.base_params)r = requests.post('http://upload.chaojiying.net/Upload/ReportError.php', data=params, headers=self.headers)return r.json()

def getCodeImgText(imgPath,imgType):chaojiying = Chaojiying_Client('bobo328410948', 'bobo328410948', '899370')#用户中心>>软件ID 生成一个替换 96001im = open(imgPath, 'rb').read()#本地图片文件路径 来替换 a.jpg 有时WIN系统须要//return chaojiying.PostPic(im,imgType)['pic_str']

#古诗文网的验证码识别操作
url = 'https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx'
page_text = requests.get(url,headers=headers).text
tree = etree.HTML(page_text)
img_src = 'https://so.gushiwen.org'+tree.xpath('//*[@id="imgCode"]/@src')[0]
print(img_src)
img_data = requests.get(url=img_src,headers=headers).content
with open('codeImg.jpg','wb') as fp:fp.write(img_data)
#进行验证码的识别
getCodeImgText('codeImg.jpg',1004)

s = requests.Session()
#模拟登陆
#古诗文网的验证码识别操作
url = 'https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx'
page_text = s.get(url,headers=headers).text
tree = etree.HTML(page_text)
img_src = 'https://so.gushiwen.org'+tree.xpath('//*[@id="imgCode"]/@src')[0]
img_data = s.get(url=img_src,headers=headers).content
with open('codeImg.jpg','wb') as fp:fp.write(img_data)#解析动态变化的请求参数
__VIEWSTATE = tree.xpath('//input[@id="__VIEWSTATE"]/@value')[0]
__VIEWSTATEGENERATOR = tree.xpath('//input[@id="__VIEWSTATEGENERATOR"]/@value')[0]
print(__VIEWSTATE,__VIEWSTATEGENERATOR)
#进行验证码的识别
code_text = getCodeImgText('codeImg.jpg',1004)
print(code_text)
login_url = 'https://so.gushiwen.org/user/login.aspx?from=http%3a%2f%2fso.gushiwen.org%2fuser%2fcollect.aspx'
data = {#下面两个请求参数是动态变化#通长情况下动态变化的请求参数会被隐藏在前台页面中'__VIEWSTATE': __VIEWSTATE,'__VIEWSTATEGENERATOR': __VIEWSTATEGENERATOR,'from': 'http://so.gushiwen.org/user/collect.aspx','email': 'www.zhangbowudi@qq.com','pwd': 'bobo328410948','code': code_text,'denglu': '登录',
}
#登陆成功之后对应的首页页面源码
main_page_text = s.post(url=login_url,headers=headers,data=data).text
with open('./main.html','w',encoding='utf-8') as fp:fp.write(main_page_text)