1.代理
代理服务器，可以接受请求然后将其转发
1.匿名度
1. 高匿:不知道你使用了代理,也不知道你的真实ip
2. 匿名: 知道你使用了代理,但是不知道你的真实ip
3. 透明:知道你使用了代理并且知道你的真实ip
2.类型
http https
3.免费代理的网站
- http://www.goubanjia.com/ - 快代理 - 西祠代理 - http://http.zhiliandaili.cn/
构建代理池：
# 构建代理池
import requests
from lxml import etree
headers = {
‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36‘,
‘Connection‘: "close"
}
#从代理精灵中提取代理ip
ip_url = ‘http://t.11jsq.com/index.php/api/entry?method=proxyServer.generate_api_url&packid=1&fa=0&fetch_key=&groupid=0&qty=4&time=1&pro=&city=&port=1&format=html&ss=5&css=&dt=1&specialTxt=3&specialJson=&usertype=2‘
page_text = requests.get(ip_url, headers=headers).text
tree = etree.HTML(page_text)
ip_list = tree.xpath(‘//body//text()‘)
print(ip_list)
# 爬取西祠代理的ip
url = "https://www.xicidaili.com/nn/%d"
proxy_list_http = []
proxy_list_https = []
for page in range(1, 2):
new_url = format(url % page)
page_text = requests.get(url=new_url, headers=headers).text
tree = etree.HTML(page_text)
tree_list = tree.xpath(‘//*[@id="ip_list"]//tr‘)[1:]
for tr in tree_list:
ip = tr.xpath("./td[2]/text()")[0]
port = tr.xpath("./td[3]/text()")[0]
ip_type = tr.xpath("./td[6]/text()")[0]
if ip_type == "HTTP":
dic = {
ip_type: ip + ":" + port
}
proxy_list_http.append(dic)
else:
dic = {
ip_type: ip + ":" + port
}
proxy_list_https.append(dic)
print(len(proxy_list_http), len(proxy_list_https))
# 检测
url = "https://www/sogou.com"
for ip in proxy_list_http:
response = requests.get(url=url, headers=headers, proxies={‘https‘: ip})
if response.status_code == "200":
print("检测到可用的ip")
2.cookie的处理
手动处理：jiangcookie封装到headers中
自动处理：session对象，可以创建一个session对象，该对象的可以像requests一样进行请求发送，不同之处在于如果使用session进行请求发送的过程中产生了cookie，则cookie会被自动存储在session对象中。
#对雪球网中的新闻数据进行爬取https://xueqiu.com/
import requests
headers = {
‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36‘,
‘Cookie‘:‘aliyungf_tc=AQAAAAl2aA+kKgkAtxdwe3JmsY226Y+n; acw_tc=2760822915681668126047128e605abf3a5518432dc7f074b2c9cb26d0aa94; xq_a_token=75661393f1556aa7f900df4dc91059df49b83145; xq_r_token=29fe5e93ec0b24974bdd382ffb61d026d8350d7d; u=121568166816578; device_id=24700f9f1986800ab4fcc880530dd0ed‘
}
url = ‘https://xueqiu.com/v4/statuses/public_timeline_by_category.json?since_id=-1&max_id=20349203&count=15&category=-1‘
page_text = requests.get(url=url,headers=headers).json()
print(page_text)
import requests
headers = {
‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36‘
}
#创建session对象
session = requests.Session()
session.get(‘https://xueqiu.com‘, headers=headers)
url = ‘https://xueqiu.com/v4/statuses/public_timeline_by_category.json?since_id=-1&max_id=20349203&count=15&category=-1‘
page_text = session.get(url=url, headers=headers).json()
print(page_text)
3.模拟登陆
1.验证码识别
相关网站
- 超级鹰：http://www.chaojiying.com/about.html
-
- 注册：（用户中心身份）
- 登陆：
- 创建一个软件：
- 下载实例代码
- 打码兔
- 云打码
识别古诗文网中的验证码
# 超级鹰的实例代码
import requests
from hashlib import md5
from lxml import etree
class Chaojiying_Client(object):
def __init__(self, username, password, soft_id):
self.username = username
password = password.encode(‘utf8‘)
self.password = md5(password).hexdigest()
self.soft_id = soft_id
self.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()
# 1.识别古诗文网站中的验证码
def tranformImgData(imgpath,t_type):
chaojiying = Chaojiying_Client(‘15879478962‘, ‘15879478962‘, ‘901492‘) # 超级鹰用户名，超级鹰用户名密码，软件id
im = open(imgPath, ‘rb‘).read()
return chaojiying.PostPic(im, t_type)[‘pic_str‘]
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]
img_data = requests.get(img_src,headers=headers).content
with open("./code.jpg","wb") as fp:
fp.write(img_data)
tranformImgData(‘./code.jpg‘,1004)
古诗文的模拟登陆
# 超级鹰的实例代码
import requests
from hashlib import md5
from lxml import etree
class Chaojiying_Client(object):
def __init__(self, username, password, soft_id):
self.username = username
password = password.encode(‘utf8‘)
self.password = md5(password).hexdigest()
self.soft_id = soft_id
self.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()
# 1.识别古诗文网站中的验证码
def tranformImgData(imgpath,t_type):
chaojiying = Chaojiying_Client(‘[email protected]‘, ‘3089693229‘, ‘901492‘)
im = open(imgPath, ‘rb‘).read()
return chaojiying.PostPic(im, t_type)[‘pic_str‘]
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]
img_data = requests.get(img_src,headers=headers).content
with open("./code.jpg","wb") as fp:
fp.write(img_data)
# 模拟登陆
s = requests.Session()
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(img_src,headers=headers).content
with open("./code.jpg",‘wb‘) as fp:
fp.write(img_data)
# 动态获取变化的请求参数
# - 动态变化的请求参数
# - 通常情况下动态变化的请求参数都会被隐藏在前台页面源码中
__VIEWSTATE = tree.xpath(‘//*[@id="__VIEWSTATE"]/@value‘)[0]
__VIEWSTATEGENERATOR = tree.xpath(‘//*[@id="__VIEWSTATEGENERATOR"]/@value‘)[0]
code_text = tranformImgData(‘./code.jpg‘,1004)
login_url = "https://so.gushiwen.org/user/login.aspx?from=http%3a%2f%2fso.gushiwen.org%2fuser%2fcollect.aspx"
data = {
"__VIEWSTATE": __VIEWSTATE,
"__VIEWSTATEGENERATOR": __VIEWSTATEGENERATOR,
"from": "http://so.gushiwen.org/user/collect.aspx",
"email": "15879478962",
"pwd": "15879478962",
"code": code_text,
"denglu": "登录",
}
page_text = s.post(url=login_url,headers=headers,data=data).text
with open("login.html","w",encoding="utf-8") as fp:
fp.write(page_text)
原文地址：https://www.cnblogs.com/zangyue/p/12180488.html
时间： 2024-07-31 14:20:08