Q2Day79 - 武沛齐 - 博客园 (cnblogs.com)
requests
Python标准库中提供了：urllib、urllib2、httplib等模块以供Http请求，但是，它的 API 太渣了。它是为另一个时代、另一个互联网所创建的。它需要巨量的工作，甚至包括各种方法覆盖，来完成最简单的任务。
Requests 是使用 Apache2 Licensed 许可证的 基于Python开发的HTTP 库，其在Python内置模块的基础上进行了高度的封装，从而使得Pythoner进行网络请求时，变得美好了许多，使用Requests可以轻而易举的完成浏览器可有的任何操作。
1、GET请求
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
|
# 1、无参数实例 import requests ret = requests.get('https://github.com/timeline.json') print ret.urlprint ret.text # 2、有参数实例 import requests payload = {'key1': 'value1', 'key2': 'value2'}ret = requests.get("http://httpbin.org/get", params=payload) print ret.urlprint ret.text |
2、POST请求
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
|
# 1、基本POST实例 import requests payload = {'key1': 'value1', 'key2': 'value2'}ret = requests.post("http://httpbin.org/post", data=payload) print ret.text # 2、发送请求头和数据实例 import requestsimport json url = 'https://api.github.com/some/endpoint'payload = {'some': 'data'}headers = {'content-type': 'application/json'} ret = requests.post(url, data=json.dumps(payload), headers=headers) print ret.textprint ret.cookies |
3、其他请求
|
1
2
3
4
5
6
7
8
9
10
|
requests.get(url, params=None, **kwargs)requests.post(url, data=None, json=None, **kwargs)requests.put(url, data=None, **kwargs)requests.head(url, **kwargs)requests.delete(url, **kwargs)requests.patch(url, data=None, **kwargs)requests.options(url, **kwargs) # 以上方法均是在此方法的基础上构建requests.request(method, url, **kwargs) |
4、更多参数
参数列表 参数示例官方文档：http://cn.python-requests.org/zh_CN/latest/user/quickstart.html#id4
BeautifulSoup
BeautifulSoup是一个模块，该模块用于接收一个HTML或XML字符串，然后将其进行格式化，之后遍可以使用他提供的方法进行快速查找指定元素，从而使得在HTML或XML中查找指定元素变得简单。
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
|
from bs4 import BeautifulSouphtml_doc = """<html><head><title>The Dormouse's story</title></head><body>asdf <div class="title"> <b>The Dormouse's story总共</b> <h1>f</h1> </div><div class="story">Once upon a time there were three little sisters; and their names were <a class="sister0" id="link1">Els<span>f</span>ie</a>, <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;and they lived at the bottom of a well.</div>ad<br/>sf<p class="story">...</p></body></html>"""soup = BeautifulSoup(html_doc, features="lxml")# 找到第一个a标签tag1 = soup.find(name='a')# 找到所有的a标签tag2 = soup.find_all(name='a')# 找到id＝link2的标签tag3 = soup.select('#link2') |
安装：
|
1
|
pip3 install beautifulsoup4 |
使用示例：
|
1
2
3
4
5
6
7
8
9
10
11
|
from bs4 import BeautifulSouphtml_doc = """<html><head><title>The Dormouse's story</title></head><body> ...</body></html>"""soup = BeautifulSoup(html_doc, features="lxml") |
1. name，标签名称
2. attr，标签属性
3. children,所有子标签
|
1
2
|
# body = soup.find('body')# v = body.children |
4. children,所有子子孙孙标签
5. clear,将标签的所有子标签全部清空（保留标签名）
6. decompose,递归的删除所有的标签
7. extract,递归的删除所有的标签，并获取删除的标签
8. decode,转换为字符串（含当前标签）；decode_contents（不含当前标签）
9. encode,转换为字节（含当前标签）；encode_contents（不含当前标签）
10. find,获取匹配的第一个标签
11. find_all,获取匹配的所有标签
12. has_attr,检查标签是否具有该属性
13. get_text,获取标签内部文本内容
14. index,检查标签在某标签中的索引位置
|
1
2
3
4
5
6
7
|
# tag = soup.find('body')# v = tag.index(tag.find('div'))# print(v)# tag = soup.find('body')# for i,v in enumerate(tag):# print(i,v) |
15. is_empty_element,是否是空标签(是否可以是空)或者自闭合标签，
判断是否是如下标签：'br' , 'hr', 'input', 'img', 'meta','spacer', 'link', 'frame', 'base'
16. 当前的关联标签
17. 查找某标签的关联标签
18. select,select_one, CSS选择器
19. 标签的内容
20.append在当前标签内部追加一个标签
21.insert在当前标签内部指定位置插入一个标签
22. insert_after,insert_before 在当前标签后面或前面插入
23. replace_with 在当前标签替换为指定标签
24. 创建标签之间的关系
25. wrap，将指定标签把当前标签包裹起来
26. unwrap，去掉当前标签，将保留其包裹的标签
|
1
2
3
|
# tag = soup.find('a')# v = tag.unwrap()# print(soup) |
更多参数官方：http://beautifulsoup.readthedocs.io/zh_CN/v4.4.0/
一大波"自动登陆"示例
#!/usr/bin/env python
# -*- coding:utf-8 -*-
import requests
# ############## 方式一 ##############
"""
# ## 1、首先登陆任何页面，获取cookie
i1 = requests.get(url="http://dig.chouti.com/help/service")
i1_cookies = i1.cookies.get_dict()
# ## 2、用户登陆，携带上一次的cookie，后台对cookie中的 gpsd 进行授权
i2 = requests.post(
url="http://dig.chouti.com/login",
data={
'phone': "8615131255089",
'password': "xxooxxoo",
'oneMonth': ""
},
cookies=i1_cookies
)
# ## 3、点赞（只需要携带已经被授权的gpsd即可）
gpsd = i1_cookies['gpsd']
i3 = requests.post(
url="http://dig.chouti.com/link/vote?linksId=8589523",
cookies={'gpsd': gpsd}
)
print(i3.text)
"""
# ############## 方式二 ##############
"""
import requests
session = requests.Session()
i1 = session.get(url="http://dig.chouti.com/help/service")
i2 = session.post(
url="http://dig.chouti.com/login",
data={
'phone': "8615131255089",
'password': "xxooxxoo",
'oneMonth': ""
}
)
i3 = session.post(
url="http://dig.chouti.com/link/vote?linksId=8589523"
)
print(i3.text)
"""
#!/usr/bin/env python
# -*- coding:utf-8 -*-
import requests
from bs4 import BeautifulSoup
# ############## 方式一 ##############
#
# # 1. 访问登陆页面，获取 authenticity_token
# i1 = requests.get('https://github.com/login')
# soup1 = BeautifulSoup(i1.text, features='lxml')
# tag = soup1.find(name='input', attrs={'name': 'authenticity_token'})
# authenticity_token = tag.get('value')
# c1 = i1.cookies.get_dict()
# i1.close()
#
# # 1. 携带authenticity_token和用户名密码等信息，发送用户验证
# form_data = {
# "authenticity_token": authenticity_token,
# "utf8": "",
# "commit": "Sign in",
# "login": "wupeiqi@live.com",
# 'password': 'xxoo'
# }
#
# i2 = requests.post('https://github.com/session', data=form_data, cookies=c1)
# c2 = i2.cookies.get_dict()
# c1.update(c2)
# i3 = requests.get('https://github.com/settings/repositories', cookies=c1)
#
# soup3 = BeautifulSoup(i3.text, features='lxml')
# list_group = soup3.find(name='div', class_='listgroup')
#
# from bs4.element import Tag
#
# for child in list_group.children:
# if isinstance(child, Tag):
# project_tag = child.find(name='a', class_='mr-1')
# size_tag = child.find(name='small')
# temp = "项目:%s(%s); 项目路径:%s" % (project_tag.get('href'), size_tag.string, project_tag.string, )
# print(temp)
# ############## 方式二 ##############
# session = requests.Session()
# # 1. 访问登陆页面，获取 authenticity_token
# i1 = session.get('https://github.com/login')
# soup1 = BeautifulSoup(i1.text, features='lxml')
# tag = soup1.find(name='input', attrs={'name': 'authenticity_token'})
# authenticity_token = tag.get('value')
# c1 = i1.cookies.get_dict()
# i1.close()
#
# # 1. 携带authenticity_token和用户名密码等信息，发送用户验证
# form_data = {
# "authenticity_token": authenticity_token,
# "utf8": "",
# "commit": "Sign in",
# "login": "wupeiqi@live.com",
# 'password': 'xxoo'
# }
#
# i2 = session.post('https://github.com/session', data=form_data)
# c2 = i2.cookies.get_dict()
# c1.update(c2)
# i3 = session.get('https://github.com/settings/repositories')
#
# soup3 = BeautifulSoup(i3.text, features='lxml')
# list_group = soup3.find(name='div', class_='listgroup')
#
# from bs4.element import Tag
#
# for child in list_group.children:
# if isinstance(child, Tag):
# project_tag = child.find(name='a', class_='mr-1')
# size_tag = child.find(name='small')
# temp = "项目:%s(%s); 项目路径:%s" % (project_tag.get('href'), size_tag.string, project_tag.string, )
# print(temp)
#!/usr/bin/env python
# -*- coding:utf-8 -*-
import time
import requests
from bs4 import BeautifulSoup
session = requests.Session()
i1 = session.get(
url='https://www.zhihu.com/#signin',
headers={
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36',
}
)
soup1 = BeautifulSoup(i1.text, 'lxml')
xsrf_tag = soup1.find(name='input', attrs={'name': '_xsrf'})
xsrf = xsrf_tag.get('value')
current_time = time.time()
i2 = session.get(
url='https://www.zhihu.com/captcha.gif',
params={'r': current_time, 'type': 'login'},
headers={
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36',
})
with open('zhihu.gif', 'wb') as f:
f.write(i2.content)
captcha = input('请打开zhihu.gif文件，查看并输入验证码：')
form_data = {
"_xsrf": xsrf,
'password': 'xxooxxoo',
"captcha": 'captcha',
'email': '424662508@qq.com'
}
i3 = session.post(
url='https://www.zhihu.com/login/email',
data=form_data,
headers={
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36',
}
)
i4 = session.get(
url='https://www.zhihu.com/settings/profile',
headers={
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36',
}
)
soup4 = BeautifulSoup(i4.text, 'lxml')
tag = soup4.find(id='rename-section')
nick_name = tag.find('span',class_='name').string
print(nick_name)
#!/usr/bin/env python
# -*- coding:utf-8 -*-
import re
import json
import base64
import rsa
import requests
def js_encrypt(text):
b64der = 'MIGfMA0GCSqGSIb3DQEBAQUAA4GNADCBiQKBgQCp0wHYbg/NOPO3nzMD3dndwS0MccuMeXCHgVlGOoYyFwLdS24Im2e7YyhB0wrUsyYf0/nhzCzBK8ZC9eCWqd0aHbdgOQT6CuFQBMjbyGYvlVYU2ZP7kG9Ft6YV6oc9ambuO7nPZh+bvXH0zDKfi02prknrScAKC0XhadTHT3Al0QIDAQAB'
der = base64.standard_b64decode(b64der)
pk = rsa.PublicKey.load_pkcs1_openssl_der(der)
v1 = rsa.encrypt(bytes(text, 'utf8'), pk)
value = base64.encodebytes(v1).replace(b'\n', b'')
value = value.decode('utf8')
return value
session = requests.Session()
i1 = session.get('https://passport.cnblogs.com/user/signin')
rep = re.compile("'VerificationToken': '(.*)'")
v = re.search(rep, i1.text)
verification_token = v.group(1)
form_data = {
'input1': js_encrypt('wptawy'),
'input2': js_encrypt('asdfasdf'),
'remember': False
}
i2 = session.post(url='https://passport.cnblogs.com/user/signin',
data=json.dumps(form_data),
headers={
'Content-Type': 'application/json; charset=UTF-8',
'X-Requested-With': 'XMLHttpRequest',
'VerificationToken': verification_token}
)
i3 = session.get(url='https://i.cnblogs.com/EditDiary.aspx')
print(i3.text)
#!/usr/bin/env python
# -*- coding:utf-8 -*-
import requests
# 第一步：访问登陆页,拿到X_Anti_Forge_Token，X_Anti_Forge_Code
# 1、请求url:https://passport.lagou.com/login/login.html
# 2、请求方法:GET
# 3、请求头:
# User-agent
r1 = requests.get('https://passport.lagou.com/login/login.html',
headers={
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',
},
)
X_Anti_Forge_Token = re.findall("X_Anti_Forge_Token = '(.*?)'", r1.text, re.S)[0]
X_Anti_Forge_Code = re.findall("X_Anti_Forge_Code = '(.*?)'", r1.text, re.S)[0]
print(X_Anti_Forge_Token, X_Anti_Forge_Code)
# print(r1.cookies.get_dict())
# 第二步：登陆
# 1、请求url:https://passport.lagou.com/login/login.json
# 2、请求方法:POST
# 3、请求头:
# cookie
# User-agent
# Referer:https://passport.lagou.com/login/login.html
# X-Anit-Forge-Code:53165984
# X-Anit-Forge-Token:3b6a2f62-80f0-428b-8efb-ef72fc100d78
# X-Requested-With:XMLHttpRequest
# 4、请求体：
# isValidate:true
# username:15131252215
# password:ab18d270d7126ea65915c50288c22c0d
# request_form_verifyCode:''
# submit:''
r2 = requests.post(
'https://passport.lagou.com/login/login.json',
headers={
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',
'Referer': 'https://passport.lagou.com/login/login.html',
'X-Anit-Forge-Code': X_Anti_Forge_Code,
'X-Anit-Forge-Token': X_Anti_Forge_Token,
'X-Requested-With': 'XMLHttpRequest'
},
data={
"isValidate": True,
'username': '15131255089',
'password': 'ab18d270d7126ea65915c50288c22c0d',
'request_form_verifyCode': '',
'submit': ''
},
cookies=r1.cookies.get_dict()
)
print(r2.text)
拉钩参考：猛击这里
