requests and BeautifulSoup

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.url
print 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.url
print 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 requests
import 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.text
print 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

 1 def request(method, url, **kwargs):
 2     """Constructs and sends a :class:`Request <Request>`.
 3 
 4     :param method: method for the new :class:`Request` object.
 5     :param url: URL for the new :class:`Request` object.
 6     :param params: (optional) Dictionary or bytes to be sent in the query string for the :class:`Request`.
 7     :param data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`.
 8     :param json: (optional) json data to send in the body of the :class:`Request`.
 9     :param headers: (optional) Dictionary of HTTP Headers to send with the :class:`Request`.
10     :param cookies: (optional) Dict or CookieJar object to send with the :class:`Request`.
11     :param files: (optional) Dictionary of ``'name': file-like-objects`` (or ``{'name': file-tuple}``) for multipart encoding upload.
12         ``file-tuple`` can be a 2-tuple ``('filename', fileobj)``, 3-tuple ``('filename', fileobj, 'content_type')``
13         or a 4-tuple ``('filename', fileobj, 'content_type', custom_headers)``, where ``'content-type'`` is a string
14         defining the content type of the given file and ``custom_headers`` a dict-like object containing additional headers
15         to add for the file.
16     :param auth: (optional) Auth tuple to enable Basic/Digest/Custom HTTP Auth.
17     :param timeout: (optional) How long to wait for the server to send data
18         before giving up, as a float, or a :ref:`(connect timeout, read
19         timeout) <timeouts>` tuple.
20     :type timeout: float or tuple
21     :param allow_redirects: (optional) Boolean. Set to True if POST/PUT/DELETE redirect following is allowed.
22     :type allow_redirects: bool
23     :param proxies: (optional) Dictionary mapping protocol to the URL of the proxy.
24     :param verify: (optional) whether the SSL cert will be verified. A CA_BUNDLE path can also be provided. Defaults to ``True``.
25     :param stream: (optional) if ``False``, the response content will be immediately downloaded.
26     :param cert: (optional) if String, path to ssl client cert file (.pem). If Tuple, ('cert', 'key') pair.
27     :return: :class:`Response <Response>` object
28     :rtype: requests.Response
29 
30     Usage::
31 
32       >>> import requests
33       >>> req = requests.request('GET', 'http://httpbin.org/get')
34       <Response [200]>
35     """
36 
37 参数列表
View Code
  1 def param_method_url():
  2     # requests.request(method='get', url='http://127.0.0.1:8000/test/')
  3     # requests.request(method='post', url='http://127.0.0.1:8000/test/')
  4     pass
  5 
  6 
  7 def param_param():
  8     # - 可以是字典
  9     # - 可以是字符串
 10     # - 可以是字节（ascii编码以内）
 11 
 12     # requests.request(method='get',
 13     # url='http://127.0.0.1:8000/test/',
 14     # params={'k1': 'v1', 'k2': '水电费'})
 15 
 16     # requests.request(method='get',
 17     # url='http://127.0.0.1:8000/test/',
 18     # params="k1=v1&k2=水电费&k3=v3&k3=vv3")
 19 
 20     # requests.request(method='get',
 21     # url='http://127.0.0.1:8000/test/',
 22     # params=bytes("k1=v1&k2=k2&k3=v3&k3=vv3", encoding='utf8'))
 23 
 24     # 错误
 25     # requests.request(method='get',
 26     # url='http://127.0.0.1:8000/test/',
 27     # params=bytes("k1=v1&k2=水电费&k3=v3&k3=vv3", encoding='utf8'))
 28     pass
 29 
 30 
 31 def param_data():
 32     # 可以是字典
 33     # 可以是字符串
 34     # 可以是字节
 35     # 可以是文件对象
 36 
 37     # requests.request(method='POST',
 38     # url='http://127.0.0.1:8000/test/',
 39     # data={'k1': 'v1', 'k2': '水电费'})
 40 
 41     # requests.request(method='POST',
 42     # url='http://127.0.0.1:8000/test/',
 43     # data="k1=v1; k2=v2; k3=v3; k3=v4"
 44     # )
 45 
 46     # requests.request(method='POST',
 47     # url='http://127.0.0.1:8000/test/',
 48     # data="k1=v1;k2=v2;k3=v3;k3=v4",
 49     # headers={'Content-Type': 'application/x-www-form-urlencoded'}
 50     # )
 51 
 52     # requests.request(method='POST',
 53     # url='http://127.0.0.1:8000/test/',
 54     # data=open('data_file.py', mode='r', encoding='utf-8'), # 文件内容是：k1=v1;k2=v2;k3=v3;k3=v4
 55     # headers={'Content-Type': 'application/x-www-form-urlencoded'}
 56     # )
 57     pass
 58 
 59 
 60 def param_json():
 61     # 将json中对应的数据进行序列化成一个字符串，json.dumps(...)
 62     # 然后发送到服务器端的body中，并且Content-Type是 {'Content-Type': 'application/json'}
 63     requests.request(method='POST',
 64                      url='http://127.0.0.1:8000/test/',
 65                      json={'k1': 'v1', 'k2': '水电费'})
 66 
 67 
 68 def param_headers():
 69     # 发送请求头到服务器端
 70     requests.request(method='POST',
 71                      url='http://127.0.0.1:8000/test/',
 72                      json={'k1': 'v1', 'k2': '水电费'},
 73                      headers={'Content-Type': 'application/x-www-form-urlencoded'}
 74                      )
 75 
 76 
 77 def param_cookies():
 78     # 发送Cookie到服务器端
 79     requests.request(method='POST',
 80                      url='http://127.0.0.1:8000/test/',
 81                      data={'k1': 'v1', 'k2': 'v2'},
 82                      cookies={'cook1': 'value1'},
 83                      )
 84     # 也可以使用CookieJar（字典形式就是在此基础上封装）
 85     from http.cookiejar import CookieJar
 86     from http.cookiejar import Cookie
 87 
 88     obj = CookieJar()
 89     obj.set_cookie(Cookie(version=0, name='c1', value='v1', port=None, domain='', path='/', secure=False, expires=None,
 90                           discard=True, comment=None, comment_url=None, rest={'HttpOnly': None}, rfc2109=False,
 91                           port_specified=False, domain_specified=False, domain_initial_dot=False, path_specified=False)
 92                    )
 93     requests.request(method='POST',
 94                      url='http://127.0.0.1:8000/test/',
 95                      data={'k1': 'v1', 'k2': 'v2'},
 96                      cookies=obj)
 97 
 98 
 99 def param_files():
100     # 发送文件
101     # file_dict = {
102     # 'f1': open('readme', 'rb')
103     # }
104     # requests.request(method='POST',
105     # url='http://127.0.0.1:8000/test/',
106     # files=file_dict)
107 
108     # 发送文件，定制文件名
109     # file_dict = {
110     # 'f1': ('test.txt', open('readme', 'rb'))
111     # }
112     # requests.request(method='POST',
113     # url='http://127.0.0.1:8000/test/',
114     # files=file_dict)
115 
116     # 发送文件，定制文件名
117     # file_dict = {
118     # 'f1': ('test.txt', "hahsfaksfa9kasdjflaksdjf")
119     # }
120     # requests.request(method='POST',
121     # url='http://127.0.0.1:8000/test/',
122     # files=file_dict)
123 
124     # 发送文件，定制文件名
125     # file_dict = {
126     #     'f1': ('test.txt', "hahsfaksfa9kasdjflaksdjf", 'application/text', {'k1': '0'})
127     # }
128     # requests.request(method='POST',
129     #                  url='http://127.0.0.1:8000/test/',
130     #                  files=file_dict)
131 
132     pass
133 
134 
135 def param_auth():
136     from requests.auth import HTTPBasicAuth, HTTPDigestAuth
137 
138     ret = requests.get('https://api.github.com/user', auth=HTTPBasicAuth('wupeiqi', 'sdfasdfasdf'))
139     print(ret.text)
140 
141     # ret = requests.get('http://192.168.1.1',
142     # auth=HTTPBasicAuth('admin', 'admin'))
143     # ret.encoding = 'gbk'
144     # print(ret.text)
145 
146     # ret = requests.get('http://httpbin.org/digest-auth/auth/user/pass', auth=HTTPDigestAuth('user', 'pass'))
147     # print(ret)
148     #
149 
150 
151 def param_timeout():
152     # ret = requests.get('http://google.com/', timeout=1)
153     # print(ret)
154 
155     # ret = requests.get('http://google.com/', timeout=(5, 1))
156     # print(ret)
157     pass
158 
159 
160 def param_allow_redirects():
161     ret = requests.get('http://127.0.0.1:8000/test/', allow_redirects=False)
162     print(ret.text)
163 
164 
165 def param_proxies():
166     # proxies = {
167     # "http": "61.172.249.96:80",
168     # "https": "http://61.185.219.126:3128",
169     # }
170 
171     # proxies = {'http://10.20.1.128': 'http://10.10.1.10:5323'}
172 
173     # ret = requests.get("http://www.proxy360.cn/Proxy", proxies=proxies)
174     # print(ret.headers)
175 
176 
177     # from requests.auth import HTTPProxyAuth
178     #
179     # proxyDict = {
180     # 'http': '77.75.105.165',
181     # 'https': '77.75.105.165'
182     # }
183     # auth = HTTPProxyAuth('username', 'mypassword')
184     #
185     # r = requests.get("http://www.google.com", proxies=proxyDict, auth=auth)
186     # print(r.text)
187 
188     pass
189 
190 
191 def param_stream():
192     ret = requests.get('http://127.0.0.1:8000/test/', stream=True)
193     print(ret.content)
194     ret.close()
195 
196     # from contextlib import closing
197     # with closing(requests.get('http://httpbin.org/get', stream=True)) as r:
198     # # 在此处理响应。
199     # for i in r.iter_content():
200     # print(i)
201 
202 
203 def requests_session():
204     import requests
205 
206     session = requests.Session()
207 
208     ### 1、首先登陆任何页面，获取cookie
209 
210     i1 = session.get(url="http://dig.chouti.com/help/service")
211 
212     ### 2、用户登陆，携带上一次的cookie，后台对cookie中的 gpsd 进行授权
213     i2 = session.post(
214         url="http://dig.chouti.com/login",
215         data={
216             'phone': "8615131255089",
217             'password': "xxxxxx",
218             'oneMonth': ""
219         }
220     )
221 
222     i3 = session.post(
223         url="http://dig.chouti.com/link/vote?linksId=8589623",
224     )
225     print(i3.text)
226 
227 参数示例
View Code

 

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 BeautifulSoup
 
html_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 BeautifulSoup
 
html_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

1
2
3
4
5
# tag = soup.find('a')
# name = tag.name # 获取
# print(name)
# tag.name = 'span' # 设置
# print(soup)

2. attr，标签属性

1
2
3
4
5
6
# tag = soup.find('a')
# attrs = tag.attrs    # 获取
# print(attrs)
# tag.attrs = {'ik':123} # 设置
# tag.attrs['id'] = 'iiiii' # 设置
# print(soup)

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

1
2
# body = soup.find('body')
# v = body.descendants

5. clear,将标签的所有子标签全部清空（保留标签名）

1
2
3
# tag = soup.find('body')
# tag.clear()
# print(soup)

6. decompose,递归的删除所有的标签

1
2
3
# body = soup.find('body')
# body.decompose()
# print(soup)

7. extract,递归的删除所有的标签，并获取删除的标签

1
2
3
# body = soup.find('body')
# v = body.extract()
# print(soup)

8. decode,转换为字符串（含当前标签）；decode_contents（不含当前标签）

1
2
3
4
# body = soup.find('body')
# v = body.decode()
# v = body.decode_contents()
# print(v)

9. encode,转换为字节（含当前标签）；encode_contents（不含当前标签）

1
2
3
4
# body = soup.find('body')
# v = body.encode()
# v = body.encode_contents()
# print(v)

10. find,获取匹配的第一个标签

1
2
3
4
5
# tag = soup.find('a')
# print(tag)
# tag = soup.find(name='a', attrs={'class': 'sister'}, recursive=True, text='Lacie')
# tag = soup.find(name='a', class_='sister', recursive=True, text='Lacie')
# print(tag)

11. find_all,获取匹配的所有标签

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
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
# tags = soup.find_all('a')
# print(tags)
 
# tags = soup.find_all('a',limit=1)
# print(tags)
 
# tags = soup.find_all(name='a', attrs={'class': 'sister'}, recursive=True, text='Lacie')
# # tags = soup.find(name='a', class_='sister', recursive=True, text='Lacie')
# print(tags)
 
 
# ####### 列表 #######
# v = soup.find_all(name=['a','div'])
# print(v)
 
# v = soup.find_all(class_=['sister0', 'sister'])
# print(v)
 
# v = soup.find_all(text=['Tillie'])
# print(v, type(v[0]))
 
 
# v = soup.find_all(id=['link1','link2'])
# print(v)
 
# v = soup.find_all(href=['link1','link2'])
# print(v)
 
# ####### 正则 #######
import re
# rep = re.compile('p')
# rep = re.compile('^p')
# v = soup.find_all(name=rep)
# print(v)
 
# rep = re.compile('sister.*')
# v = soup.find_all(class_=rep)
# print(v)
 
# rep = re.compile('http://www.oldboy.com/static/.*')
# v = soup.find_all(href=rep)
# print(v)
 
# ####### 方法筛选 #######
# def func(tag):
# return tag.has_attr('class') and tag.has_attr('id')
# v = soup.find_all(name=func)
# print(v)
 
 
# ## get,获取标签属性
# tag = soup.find('a')
# v = tag.get('id')
# print(v)

12. has_attr,检查标签是否具有该属性

1
2
3
# tag = soup.find('a')
# v = tag.has_attr('id')
# print(v)

13. get_text,获取标签内部文本内容

1
2
3
# tag = soup.find('a')
# v = tag.get_text('id')
# print(v)

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'

1
2
3
# tag = soup.find('br')
# v = tag.is_empty_element
# print(v)

16. 当前的关联标签

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
# soup.next
# soup.next_element
# soup.next_elements
# soup.next_sibling
# soup.next_siblings
 
#
# tag.previous
# tag.previous_element
# tag.previous_elements
# tag.previous_sibling
# tag.previous_siblings
 
#
# tag.parent
# tag.parents

17. 查找某标签的关联标签

1
2
3
4
5
6
7
8
9
10
11
12
13
14
# tag.find_next(...)
# tag.find_all_next(...)
# tag.find_next_sibling(...)
# tag.find_next_siblings(...)
 
# tag.find_previous(...)
# tag.find_all_previous(...)
# tag.find_previous_sibling(...)
# tag.find_previous_siblings(...)
 
# tag.find_parent(...)
# tag.find_parents(...)
 
# 参数同find_all

18. select,select_one, CSS选择器

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
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
soup.select("title")
 
soup.select("p nth-of-type(3)")
 
soup.select("body a")
 
soup.select("html head title")
 
tag = soup.select("span,a")
 
soup.select("head > title")
 
soup.select("p > a")
 
soup.select("p > a:nth-of-type(2)")
 
soup.select("p > #link1")
 
soup.select("body > a")
 
soup.select("#link1 ~ .sister")
 
soup.select("#link1 + .sister")
 
soup.select(".sister")
 
soup.select("[class~=sister]")
 
soup.select("#link1")
 
soup.select("a#link2")
 
soup.select('a[href]')
 
soup.select('a[href="http://example.com/elsie"]')
 
soup.select('a[href^="http://example.com/"]')
 
soup.select('a[href$="tillie"]')
 
soup.select('a[href*=".com/el"]')
 
 
from bs4.element import Tag
 
def default_candidate_generator(tag):
    for child in tag.descendants:
        if not isinstance(child, Tag):
            continue
        if not child.has_attr('href'):
            continue
        yield child
 
tags = soup.find('body').select("a", _candidate_generator=default_candidate_generator)
print(type(tags), tags)
 
from bs4.element import Tag
def default_candidate_generator(tag):
    for child in tag.descendants:
        if not isinstance(child, Tag):
            continue
        if not child.has_attr('href'):
            continue
        yield child
 
tags = soup.find('body').select("a", _candidate_generator=default_candidate_generator, limit=1)
print(type(tags), tags)

19. 标签的内容

1
2
3
4
5
6
7
8
9
10
11
12
13
# tag = soup.find('span')
# print(tag.string)          # 获取
# tag.string = 'new content' # 设置
# print(soup)
 
# tag = soup.find('body')
# print(tag.string)
# tag.string = 'xxx'
# print(soup)
 
# tag = soup.find('body')
# v = tag.stripped_strings  # 递归内部获取所有标签的文本
# print(v)

20.append在当前标签内部追加一个标签

1
2
3
4
5
6
7
8
9
10
# tag = soup.find('body')
# tag.append(soup.find('a'))
# print(soup)
#
# from bs4.element import Tag
# obj = Tag(name='i',attrs={'id': 'it'})
# obj.string = '我是一个新来的'
# tag = soup.find('body')
# tag.append(obj)
# print(soup)

21.insert在当前标签内部指定位置插入一个标签

1
2
3
4
5
6
# from bs4.element import Tag
# obj = Tag(name='i', attrs={'id': 'it'})
# obj.string = '我是一个新来的'
# tag = soup.find('body')
# tag.insert(2, obj)
# print(soup)

22. insert_after,insert_before 在当前标签后面或前面插入

1
2
3
4
5
6
7
# from bs4.element import Tag
# obj = Tag(name='i', attrs={'id': 'it'})
# obj.string = '我是一个新来的'
# tag = soup.find('body')
# # tag.insert_before(obj)
# tag.insert_after(obj)
# print(soup)

23. replace_with 在当前标签替换为指定标签

1
2
3
4
5
6
# from bs4.element import Tag
# obj = Tag(name='i', attrs={'id': 'it'})
# obj.string = '我是一个新来的'
# tag = soup.find('div')
# tag.replace_with(obj)
# print(soup)

24. 创建标签之间的关系

1
2
3
4
# tag = soup.find('div')
# a = soup.find('a')
# tag.setup(previous_sibling=a)
# print(tag.previous_sibling)

25. wrap，将指定标签把当前标签包裹起来

1
2
3
4
5
6
7
8
9
10
11
# from bs4.element import Tag
# obj1 = Tag(name='div', attrs={'id': 'it'})
# obj1.string = '我是一个新来的'
#
# tag = soup.find('a')
# v = tag.wrap(obj1)
# print(soup)
 
# tag = soup.find('a')
# v = tag.wrap(soup.find('p'))
# print(soup)

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

 1 #!/usr/bin/env python
 2 # -*- coding:utf-8 -*-
 3 import requests
 4 
 5 
 6 # ############## 方式一 ##############
 7 """
 8 # ## 1、首先登陆任何页面，获取cookie
 9 i1 = requests.get(url="http://dig.chouti.com/help/service")
10 i1_cookies = i1.cookies.get_dict()
11 
12 # ## 2、用户登陆，携带上一次的cookie，后台对cookie中的 gpsd 进行授权
13 i2 = requests.post(
14     url="http://dig.chouti.com/login",
15     data={
16         'phone': "8615131255089",
17         'password': "xxooxxoo",
18         'oneMonth': ""
19     },
20     cookies=i1_cookies
21 )
22 
23 # ## 3、点赞（只需要携带已经被授权的gpsd即可）
24 gpsd = i1_cookies['gpsd']
25 i3 = requests.post(
26     url="http://dig.chouti.com/link/vote?linksId=8589523",
27     cookies={'gpsd': gpsd}
28 )
29 
30 print(i3.text)
31 """
32 
33 
34 # ############## 方式二 ##############
35 """
36 import requests
37 
38 session = requests.Session()
39 i1 = session.get(url="http://dig.chouti.com/help/service")
40 i2 = session.post(
41     url="http://dig.chouti.com/login",
42     data={
43         'phone': "8615131255089",
44         'password': "xxooxxoo",
45         'oneMonth': ""
46     }
47 )
48 i3 = session.post(
49     url="http://dig.chouti.com/link/vote?linksId=8589523"
50 )
51 print(i3.text)
52 
53 """
抽屉新热榜
 1 #!/usr/bin/env python
 2 # -*- coding:utf-8 -*-
 3 
 4 import requests
 5 from bs4 import BeautifulSoup
 6 
 7 # ############## 方式一 ##############
 8 #
 9 # # 1. 访问登陆页面，获取 authenticity_token
10 # i1 = requests.get('https://github.com/login')
11 # soup1 = BeautifulSoup(i1.text, features='lxml')
12 # tag = soup1.find(name='input', attrs={'name': 'authenticity_token'})
13 # authenticity_token = tag.get('value')
14 # c1 = i1.cookies.get_dict()
15 # i1.close()
16 #
17 # # 1. 携带authenticity_token和用户名密码等信息，发送用户验证
18 # form_data = {
19 # "authenticity_token": authenticity_token,
20 #     "utf8": "",
21 #     "commit": "Sign in",
22 #     "login": "wupeiqi@live.com",
23 #     'password': 'xxoo'
24 # }
25 #
26 # i2 = requests.post('https://github.com/session', data=form_data, cookies=c1)
27 # c2 = i2.cookies.get_dict()
28 # c1.update(c2)
29 # i3 = requests.get('https://github.com/settings/repositories', cookies=c1)
30 #
31 # soup3 = BeautifulSoup(i3.text, features='lxml')
32 # list_group = soup3.find(name='div', class_='listgroup')
33 #
34 # from bs4.element import Tag
35 #
36 # for child in list_group.children:
37 #     if isinstance(child, Tag):
38 #         project_tag = child.find(name='a', class_='mr-1')
39 #         size_tag = child.find(name='small')
40 #         temp = "项目:%s(%s); 项目路径:%s" % (project_tag.get('href'), size_tag.string, project_tag.string, )
41 #         print(temp)
42 
43 
44 
45 # ############## 方式二 ##############
46 # session = requests.Session()
47 # # 1. 访问登陆页面，获取 authenticity_token
48 # i1 = session.get('https://github.com/login')
49 # soup1 = BeautifulSoup(i1.text, features='lxml')
50 # tag = soup1.find(name='input', attrs={'name': 'authenticity_token'})
51 # authenticity_token = tag.get('value')
52 # c1 = i1.cookies.get_dict()
53 # i1.close()
54 #
55 # # 1. 携带authenticity_token和用户名密码等信息，发送用户验证
56 # form_data = {
57 #     "authenticity_token": authenticity_token,
58 #     "utf8": "",
59 #     "commit": "Sign in",
60 #     "login": "wupeiqi@live.com",
61 #     'password': 'xxoo'
62 # }
63 #
64 # i2 = session.post('https://github.com/session', data=form_data)
65 # c2 = i2.cookies.get_dict()
66 # c1.update(c2)
67 # i3 = session.get('https://github.com/settings/repositories')
68 #
69 # soup3 = BeautifulSoup(i3.text, features='lxml')
70 # list_group = soup3.find(name='div', class_='listgroup')
71 #
72 # from bs4.element import Tag
73 #
74 # for child in list_group.children:
75 #     if isinstance(child, Tag):
76 #         project_tag = child.find(name='a', class_='mr-1')
77 #         size_tag = child.find(name='small')
78 #         temp = "项目:%s(%s); 项目路径:%s" % (project_tag.get('href'), size_tag.string, project_tag.string, )
79 #         print(temp)
github
 1 #!/usr/bin/env python
 2 # -*- coding:utf-8 -*-
 3 import time
 4 
 5 import requests
 6 from bs4 import BeautifulSoup
 7 
 8 session = requests.Session()
 9 
10 i1 = session.get(
11     url='https://www.zhihu.com/#signin',
12     headers={
13         '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',
14     }
15 )
16 
17 soup1 = BeautifulSoup(i1.text, 'lxml')
18 xsrf_tag = soup1.find(name='input', attrs={'name': '_xsrf'})
19 xsrf = xsrf_tag.get('value')
20 
21 current_time = time.time()
22 i2 = session.get(
23     url='https://www.zhihu.com/captcha.gif',
24     params={'r': current_time, 'type': 'login'},
25     headers={
26         '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',
27     })
28 
29 with open('zhihu.gif', 'wb') as f:
30     f.write(i2.content)
31 
32 captcha = input('请打开zhihu.gif文件，查看并输入验证码：')
33 form_data = {
34     "_xsrf": xsrf,
35     'password': 'xxooxxoo',
36     "captcha": 'captcha',
37     'email': '424662508@qq.com'
38 }
39 i3 = session.post(
40     url='https://www.zhihu.com/login/email',
41     data=form_data,
42     headers={
43         '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',
44     }
45 )
46 
47 i4 = session.get(
48     url='https://www.zhihu.com/settings/profile',
49     headers={
50         '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',
51     }
52 )
53 
54 soup4 = BeautifulSoup(i4.text, 'lxml')
55 tag = soup4.find(id='rename-section')
56 nick_name = tag.find('span',class_='name').string
57 print(nick_name)
知乎
 1 #!/usr/bin/env python
 2 # -*- coding:utf-8 -*-
 3 import re
 4 import json
 5 import base64
 6 
 7 import rsa
 8 import requests
 9 
10 
11 def js_encrypt(text):
12     b64der = 'MIGfMA0GCSqGSIb3DQEBAQUAA4GNADCBiQKBgQCp0wHYbg/NOPO3nzMD3dndwS0MccuMeXCHgVlGOoYyFwLdS24Im2e7YyhB0wrUsyYf0/nhzCzBK8ZC9eCWqd0aHbdgOQT6CuFQBMjbyGYvlVYU2ZP7kG9Ft6YV6oc9ambuO7nPZh+bvXH0zDKfi02prknrScAKC0XhadTHT3Al0QIDAQAB'
13     der = base64.standard_b64decode(b64der)
14 
15     pk = rsa.PublicKey.load_pkcs1_openssl_der(der)
16     v1 = rsa.encrypt(bytes(text, 'utf8'), pk)
17     value = base64.encodebytes(v1).replace(b'\n', b'')
18     value = value.decode('utf8')
19 
20     return value
21 
22 
23 session = requests.Session()
24 
25 i1 = session.get('https://passport.cnblogs.com/user/signin')
26 rep = re.compile("'VerificationToken': '(.*)'")
27 v = re.search(rep, i1.text)
28 verification_token = v.group(1)
29 
30 form_data = {
31     'input1': js_encrypt('wptawy'),
32     'input2': js_encrypt('asdfasdf'),
33     'remember': False
34 }
35 
36 i2 = session.post(url='https://passport.cnblogs.com/user/signin',
37                   data=json.dumps(form_data),
38                   headers={
39                       'Content-Type': 'application/json; charset=UTF-8',
40                       'X-Requested-With': 'XMLHttpRequest',
41                       'VerificationToken': verification_token}
42                   )
43 
44 i3 = session.get(url='https://i.cnblogs.com/EditDiary.aspx')
45 
46 print(i3.text)
博客园
 1 #!/usr/bin/env python
 2 # -*- coding:utf-8 -*-
 3 
 4 import requests
 5 
 6 
 7 # 第一步：访问登陆页,拿到X_Anti_Forge_Token，X_Anti_Forge_Code
 8 # 1、请求url:https://passport.lagou.com/login/login.html
 9 # 2、请求方法:GET
10 # 3、请求头:
11 #    User-agent
12 r1 = requests.get('https://passport.lagou.com/login/login.html',
13                  headers={
14                      'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',
15                  },
16                  )
17 
18 X_Anti_Forge_Token = re.findall("X_Anti_Forge_Token = '(.*?)'", r1.text, re.S)[0]
19 X_Anti_Forge_Code = re.findall("X_Anti_Forge_Code = '(.*?)'", r1.text, re.S)[0]
20 print(X_Anti_Forge_Token, X_Anti_Forge_Code)
21 # print(r1.cookies.get_dict())
22 # 第二步：登陆
23 # 1、请求url:https://passport.lagou.com/login/login.json
24 # 2、请求方法:POST
25 # 3、请求头:
26 #    cookie
27 #    User-agent
28 #    Referer:https://passport.lagou.com/login/login.html
29 #    X-Anit-Forge-Code:53165984
30 #    X-Anit-Forge-Token:3b6a2f62-80f0-428b-8efb-ef72fc100d78
31 #    X-Requested-With:XMLHttpRequest
32 # 4、请求体：
33 # isValidate:true
34 # username:15131252215
35 # password:ab18d270d7126ea65915c50288c22c0d
36 # request_form_verifyCode:''
37 # submit:''
38 r2 = requests.post(
39     'https://passport.lagou.com/login/login.json',
40     headers={
41         'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',
42         'Referer': 'https://passport.lagou.com/login/login.html',
43         'X-Anit-Forge-Code': X_Anti_Forge_Code,
44         'X-Anit-Forge-Token': X_Anti_Forge_Token,
45         'X-Requested-With': 'XMLHttpRequest'
46     },
47     data={
48         "isValidate": True,
49         'username': '15131255089',
50         'password': 'ab18d270d7126ea65915c50288c22c0d',
51         'request_form_verifyCode': '',
52         'submit': ''
53     },
54     cookies=r1.cookies.get_dict()
55 )
56 print(r2.text)
拉勾网

 

posted @ 2018-12-13 09:32  kiko0o0  阅读(234)  评论(0)  编辑  收藏  举报