目录

一、requests模块
二、Beautifulsoup模块

一、requests模块

1、介绍

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。

2、请求method介绍

（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')
ret.encoding = "gbk"
print(ret.url)
print(ret.text)  # str
print(ret.content)  # bytes
  
  
# 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）代理

import requests

url = "http://www.baidu.com/"

headers = {

    "User-Agent":'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:62.0) Gecko/20100101 Firefox/62.0'

}

proxies={

    'http':'113.200.56.13:8010',  # 网上随便找的一个代理，不稳定

}

res = requests.get(url=url,proxies=proxies)

res.encoding = "utf8"

print(res.text)  # 实验成功

3、参数说明

def request(method, url, **kwargs):

    """Constructs and sends a :class:`Request <Request>`.

    :param method: method for the new :class:`Request` object.

    :param url: URL for the new :class:`Request` object.

    :param params: (optional) Dictionary or bytes to be sent in the query string for the :class:`Request`.

    :param data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`.

    :param json: (optional) json data to send in the body of the :class:`Request`.

    :param headers: (optional) Dictionary of HTTP Headers to send with the :class:`Request`.

    :param cookies: (optional) Dict or CookieJar object to send with the :class:`Request`.

    :param files: (optional) Dictionary of ``'name': file-like-objects`` (or ``{'name': file-tuple}``) for multipart encoding upload.

        ``file-tuple`` can be a 2-tuple ``('filename', fileobj)``, 3-tuple ``('filename', fileobj, 'content_type')``

        or a 4-tuple ``('filename', fileobj, 'content_type', custom_headers)``, where ``'content-type'`` is a string

        defining the content type of the given file and ``custom_headers`` a dict-like object containing additional headers

        to add for the file.

    :param auth: (optional) Auth tuple to enable Basic/Digest/Custom HTTP Auth.

    :param timeout: (optional) How long to wait for the server to send data

        before giving up, as a float, or a :ref:`(connect timeout, read

        timeout) <timeouts>` tuple.

    :type timeout: float or tuple

    :param allow_redirects: (optional) Boolean. Set to True if POST/PUT/DELETE redirect following is allowed.

    :type allow_redirects: bool

    :param proxies: (optional) Dictionary mapping protocol to the URL of the proxy.

    :param verify: (optional) whether the SSL cert will be verified. A CA_BUNDLE path can also be provided. Defaults to ``True``.

    :param stream: (optional) if ``False``, the response content will be immediately downloaded.

    :param cert: (optional) if String, path to ssl client cert file (.pem). If Tuple, ('cert', 'key') pair.

    :return: :class:`Response <Response>` object

    :rtype: requests.Response

    Usage::

      >>> import requests

      >>> req = requests.request('GET', 'http://httpbin.org/get')

      <Response [200]>

    """

参数列表

参数说明

def param_method_url():

    # requests.request(method='get', url='http://127.0.0.1:8000/test/')

    # requests.request(method='post', url='http://127.0.0.1:8000/test/')

    pass

def param_param():

    # - 可以是字典

    # - 可以是字符串

    # - 可以是字节（ascii编码以内）

    # requests.request(method='get',

    # url='http://127.0.0.1:8000/test/',

    # params={'k1': 'v1', 'k2': '水电费'})

    # requests.request(method='get',

    # url='http://127.0.0.1:8000/test/',

    # params="k1=v1&k2=水电费&k3=v3&k3=vv3")

    # requests.request(method='get',

    # url='http://127.0.0.1:8000/test/',

    # params=bytes("k1=v1&k2=k2&k3=v3&k3=vv3", encoding='utf8'))

    # 错误

    # requests.request(method='get',

    # url='http://127.0.0.1:8000/test/',

    # params=bytes("k1=v1&k2=水电费&k3=v3&k3=vv3", encoding='utf8'))

    pass

def param_data():

    # 可以是字典

    # 可以是字符串

    # 可以是字节

    # 可以是文件对象

    # requests.request(method='POST',

    # url='http://127.0.0.1:8000/test/',

    # data={'k1': 'v1', 'k2': '水电费'})

    # requests.request(method='POST',

    # url='http://127.0.0.1:8000/test/',

    # data="k1=v1; k2=v2; k3=v3; k3=v4"

    # )

    # requests.request(method='POST',

    # url='http://127.0.0.1:8000/test/',

    # data="k1=v1;k2=v2;k3=v3;k3=v4",

    # headers={'Content-Type': 'application/x-www-form-urlencoded'}

    # )

    # requests.request(method='POST',

    # url='http://127.0.0.1:8000/test/',

    # data=open('data_file.py', mode='r', encoding='utf-8'), # 文件内容是：k1=v1;k2=v2;k3=v3;k3=v4

    # headers={'Content-Type': 'application/x-www-form-urlencoded'}

    # )

    pass

def param_json():

    # 将json中对应的数据进行序列化成一个字符串，json.dumps(...)

    # 然后发送到服务器端的body中，并且Content-Type是 {'Content-Type': 'application/json'}

    requests.request(method='POST',

                     url='http://127.0.0.1:8000/test/',

                     json={'k1': 'v1', 'k2': '水电费'})

def param_headers():

    # 发送请求头到服务器端

    requests.request(method='POST',

                     url='http://127.0.0.1:8000/test/',

                     json={'k1': 'v1', 'k2': '水电费'},

                     headers={'Content-Type': 'application/x-www-form-urlencoded'}

                     )

def param_cookies():

    # 发送Cookie到服务器端

    requests.request(method='POST',

                     url='http://127.0.0.1:8000/test/',

                     data={'k1': 'v1', 'k2': 'v2'},

                     cookies={'cook1': 'value1'},

                     )

    # 也可以使用CookieJar（字典形式就是在此基础上封装）

    from http.cookiejar import CookieJar

    from http.cookiejar import Cookie

    obj = CookieJar()

    obj.set_cookie(Cookie(version=0, name='c1', value='v1', port=None, domain='', path='/', secure=False, expires=None,

                          discard=True, comment=None, comment_url=None, rest={'HttpOnly': None}, rfc2109=False,

                          port_specified=False, domain_specified=False, domain_initial_dot=False, path_specified=False)

                   )

    requests.request(method='POST',

                     url='http://127.0.0.1:8000/test/',

                     data={'k1': 'v1', 'k2': 'v2'},

                     cookies=obj)

def param_files():

    # 发送文件

    # file_dict = {

    # 'f1': open('readme', 'rb')

    # }

    # requests.request(method='POST',

    # url='http://127.0.0.1:8000/test/',

    # files=file_dict)

    # 发送文件，定制文件名

    # file_dict = {

    # 'f1': ('test.txt', open('readme', 'rb'))

    # }

    # requests.request(method='POST',

    # url='http://127.0.0.1:8000/test/',

    # files=file_dict)

    # 发送文件，定制文件名

    # file_dict = {

    # 'f1': ('test.txt', "hahsfaksfa9kasdjflaksdjf")

    # }

    # requests.request(method='POST',

    # url='http://127.0.0.1:8000/test/',

    # files=file_dict)

    # 发送文件，定制文件名

    # file_dict = {

    #     'f1': ('test.txt', "hahsfaksfa9kasdjflaksdjf", 'application/text', {'k1': '0'})

    # }

    # requests.request(method='POST',

    #                  url='http://127.0.0.1:8000/test/',

    #                  files=file_dict)

    pass

def param_auth():

    from requests.auth import HTTPBasicAuth, HTTPDigestAuth

    ret = requests.get('https://api.github.com/user', auth=HTTPBasicAuth('wupeiqi', 'sdfasdfasdf'))

    print(ret.text)

    # ret = requests.get('http://192.168.1.1',

    # auth=HTTPBasicAuth('admin', 'admin'))

    # ret.encoding = 'gbk'

    # print(ret.text)

    # ret = requests.get('http://httpbin.org/digest-auth/auth/user/pass', auth=HTTPDigestAuth('user', 'pass'))

    # print(ret)

    #

def param_timeout():

    # ret = requests.get('http://google.com/', timeout=1)

    # print(ret)

    # ret = requests.get('http://google.com/', timeout=(5, 1))

    # print(ret)

    pass

def param_allow_redirects():

    ret = requests.get('http://127.0.0.1:8000/test/', allow_redirects=False)

    print(ret.text)

def param_proxies():

    # proxies = {

    # "http": "61.172.249.96:80",

    # "https": "http://61.185.219.126:3128",

    # }

    # proxies = {'http://10.20.1.128': 'http://10.10.1.10:5323'}

    # ret = requests.get("http://www.proxy360.cn/Proxy", proxies=proxies)

    # print(ret.headers)

    # from requests.auth import HTTPProxyAuth

    #

    # proxyDict = {

    # 'http': '77.75.105.165',

    # 'https': '77.75.105.165'

    # }

    # auth = HTTPProxyAuth('username', 'mypassword')

    #

    # r = requests.get("http://www.google.com", proxies=proxyDict, auth=auth)

    # print(r.text)

    pass

def param_stream():

    ret = requests.get('http://127.0.0.1:8000/test/', stream=True)

    print(ret.content)

    ret.close()

    # from contextlib import closing

    # with closing(requests.get('http://httpbin.org/get', stream=True)) as r:

    # # 在此处理响应。

    # for i in r.iter_content():

    # print(i)

def requests_session():

    import requests

    session = requests.Session()

    ### 1、首先登陆任何页面，获取cookie

    i1 = session.get(url="http://dig.chouti.com/help/service")

    ### 2、用户登陆，携带上一次的cookie，后台对cookie中的 gpsd 进行授权

    i2 = session.post(

        url="http://dig.chouti.com/login",

        data={

            'phone': "",

            'password': "xxxxxx",

            'oneMonth': ""

        }

    )

    i3 = session.post(

        url="http://dig.chouti.com/link/vote?linksId=8589623",

    )

    print(i3.text)

参数示例

官方文档：http://cn.python-requests.org/zh_CN/latest/user/quickstart.html#id4

二、Beautifulsoup模块

可参考：https://blog.csdn.net/xxf813/article/details/81605197

1、介绍

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。

2、简单使用

pip3 install beautifulsoup4

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')

简单使用

3、方法说明

1. name，标签名称

# tag = soup.find('a')

# name = tag.name # 获取

# print(name)

# tag.name = 'span' # 设置

# print(soup)

name

2. attrs，标签属性

# 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)

attr

3. children,所有子标签

# body = soup.find('body')

# v = body.children

children

4. descendants,所有子子孙孙标签

# body = soup.find('body')

# v = body.descendants

descendants

5. clear,将标签的所有子标签全部清空（保留标签名）

# tag = soup.find('body')

# tag.clear()

# print(soup)

clear

6. decompose,递归的删除所有的标签

# body = soup.find('body')

# body.decompose()

# print(soup)

decompose

7. extract,递归的删除所有的标签，并获取删除的标签。（跟父有关系）

# body = soup.find('body')

# v = body.extract()

# print(soup)

extract

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

# body = soup.find('body')

# v = body.decode()

# v = body.decode_contents()

# print(v)

decode

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

# body = soup.find('body')

# v = body.encode()

# v = body.encode_contents()

# print(v)

encode

10. find,获取匹配的第一个标签

# 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)

find

11. find_all,获取匹配的所有标签

# 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)

find_all

12. has_attr,检查标签是否具有该属性

# tag = soup.find('a')

# v = tag.has_attr('id')

# print(v)

has_attr

13. get_text,获取标签内部文本内容

# tag = soup.find('a')

# v = tag.get_text('id')

# print(v)

get_text

14. index,检查标签在某标签中的索引位置

# 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)

index

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'

# tag = soup.find('br')

# v = tag.is_empty_element

# print(v)

is_empty_element

16. 当前的关联标签

# 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

当前的关联标签（next、previous等）

17. 查找某标签的关联标签

# 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

查看某标签的关联标签

18. select,select_one, CSS选择器

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)

select，select_one，CSS选择器

19. 标签的内容

# 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)

标签内容（string等）

20.append在当前标签内部追加一个标签

# 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)

append

21.insert在当前标签内部指定位置插入一个标签

# 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)

insert

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

# 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)

insert_after,insert_before

23. replace_with 在当前标签替换为指定标签

# 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)

replace_with

24. 创建标签之间的关系

# tag = soup.find('div')

# a = soup.find('a')

# tag.setup(previous_sibling=a)

# print(tag.previous_sibling)

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

# 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)

wrap

26. unwrap，去掉当前标签，将保留其包裹的标签

# tag = soup.find('a')

# v = tag.unwrap()

# print(soup)

unwrap

更多参数官方：http://beautifulsoup.readthedocs.io/zh_CN/v4.4.0/

示例

# # -*- coding:utf-8 -*-

# import requests

# from bs4 import BeautifulSoup

#

#

# response = requests.get("http://www.autohome.com.cn/news/")

# response.encoding = "gbk"

#

# # print(type(response.text))  # str

#

#

# soup = BeautifulSoup(response.text,"html.parser")

#

# tag = soup.find(id='auto0channel0lazyload-article')

# print(tag)

# tag = soup.find(name="h3")

# print(tag)

# tag = soup.find(name="h3",attr={"class":"xxx"})

# 所有新闻

# 标题，简介，url，图片

import requests

from bs4 import BeautifulSoup

#

html = requests.get("http://www.autohome.com.cn/news/")

html.encoding = "gbk"

print(type(html.text))  # <class 'str'>

print(type(html.content))  # <class 'bytes'>

soup = BeautifulSoup(html,"html.parser")

li_list = soup.find(id="auto-channel-lazyload-article").find_all(name="li")

for li in li_list:

    title = li.find(name="h3")

    if not title:

        continue

    print('\033[1;32m[标题]\033[0m',title.text)

    summary = li.find(name="p")

    print('\033[1;33m[简介]\033[0m',summary.text)

    # attrs = li.find("a").attrs

    # print(attrs)

    url = li.find("a").get("href")

    print('\033[1;34m[url]\033[0m',url)

    img = li.find("img").get("src")

    print('\033[1;35m[img]\033[0m',img)

    res = requests.get("http:%s" % (img,))

    # file_name = img.rsplit("/",1)[1]

    # with open(file_name,"wb") as f:

    #     f.write(res.content)

    print("\033[1;31m==================================================================\033[0m")

汽车之家 某些页面

# -*- coding:utf-8 -*-

import requests

from bs4 import BeautifulSoup

# 获取token

r1 = requests.get("https://github.com/login")

r1.encoding = "gbk"

s1 = BeautifulSoup(r1.text,"html.parser")

token = s1.find(name="input",attrs={"name":"authenticity_token"}).get("value")

r1_cookie_dict = r1.cookies.get_dict()

print(token)

# 将用户名、密码、token发送到post的url

'''

commit:Sign in

utf8:✓

authenticity_token:r31RX8eQeShWRxUnEyYXtQHVmIlrw6sZmwdyy/IYP0dCzV1m4covQQZz+d8qUuc9mT8qIxjjx0U3YjKN9ZvLHA==

login:asdf

password:asdf

'''

r2 = requests.post(

    url="https://github.com/session",

    data={

        "utf8":"✓",

        "authenticity_token":token,

        "login":"fat39@163.com",

        "password":"123!@#qwe",

        "commit":"Sign in"

    },

    cookies=r1_cookie_dict,

)

r2_cookie_dict = r2.cookies.get_dict()

print(r2_cookie_dict)

# 带cookie访问

cookie_dict = {}

cookie_dict.update(r1_cookie_dict)

cookie_dict.update(r2_cookie_dict)

r3 = requests.get(

    url="https://github.com/settings/emails",

    cookies=cookie_dict,

)

print(r3.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)

自动登录github

#!/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)

知乎

知乎

#!/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)

博客园

博客园

参考or转发

http://www.cnblogs.com/wupeiqi/articles/6283017.html

python之爬虫_模块的更多相关文章

  1. Python网络爬虫-requests模块(II)

    有些时候,我们在使用爬虫程序去爬取一些用户相关信息的数据(爬取张三“人人网”个人主页数据)时,如果使用之前requests模块常规操作时,往往达不到我们想要的目的,例如: #!/usr/bin/env ...

  2. Python网络爬虫-requests模块

    requests模块 requests模块是python中原生的基于网络请求的模块,其主要作用是用来模拟浏览器发起请求.功能强大,用法简洁高效.在爬虫领域中占据着半壁江山的地位. 如何使用reques ...

  3. python之爬虫_并发（串行、多线程、多进程、异步IO）

    并发 在编写爬虫时,性能的消耗主要在IO请求中,当单进程单线程模式下请求URL时必然会引起等待,从而使得请求整体变慢 import requests def fetch_async(url): res ...

  4. python 网络爬虫requests模块

    一.requests模块 requests模块是python中原生的基于网络请求的模块,其主要作用是用来模拟浏览器发起请求.功能强大,用法简洁高效. 1.1 模块介绍及请求过程 requests模块模 ...

  5. 06 Python网络爬虫requets模块高级用法

    一. 基于requests模块的cookie操作 - cookie概念: 当用户通过浏览器访问一个域名的时候,访问的web服务器会给客户端发送数据,以保持web服务器与客户端之间的状态保持,这些数据就 ...

  6. [b0020] python 归纳 (六)_模块变量作用域

    test_module2.py: # -*- coding: utf-8 -*-"""测试 模块变量的作用域 总结:1 其他模块的变量,在当前模块的任何地方,包括函数都可 ...

  7. Python网络爬虫_爬取Ajax动态加载和翻页时url不变的网页

    1 . 什么是 AJAX ? AJAX = 异步 JavaScript 和 XML. AJAX 是一种用于创建快速动态网页的技术. 通过在后台与服务器进行少量数据交换,AJAX 可以使网页实现异步更新 ...

  8. Python网络爬虫-xpath模块

    一.正解解析 单字符: . : 除换行以外所有字符 [] :[aoe] [a-w] 匹配集合中任意一个字符 \d :数字 [0-9] \D : 非数字 \w :数字.字母.下划线.中文 \W : 非\ ...

  9. 【python网络爬虫】之requests相关模块

    python网络爬虫的学习第一步 [python网络爬虫]之0 爬虫与反扒 [python网络爬虫]之一 简单介绍 [python网络爬虫]之二 python uillib库 [python网络爬虫] ...

随机推荐

  1. bootstrap组件-导出数据

    一.需求:在我们日常工作的时候,对数据的导出有需求.比如导出JSON.XML.SQL等形式.方便我们日常使用. 二.组件:我们可以使用bootstrap的扩展插件Table Export来实现我们的需 ...

  2. cloudstack-kvm-libvirtd

    2.4.libvirtd日志和VM的日志 在运行libvirtd的时候,我们需要获得lbivirtd的运行信息.所以我们需要找到他的日志文件.一般情况下,它是在/var/log/libvirt/lib ...

  3. 3DES加解密 C语言

    3DES(或称为Triple DES),它相当于是对每个数据块应用三次DES加密算法.3*8字节密钥. 设Ek()和Dk()代表DES算法的加密和解密过程,K代表DES算法使用的密钥,P代表明文,C代 ...

  4. IOS马甲包（诚招大量开发）

    马甲包的字面意思给产品穿马甲,但是我认为马甲包更像是产品的一种分身,一种和产品一样拥有灵魂,拥有肉身的一种分身.它能为产品带来同样的功能效果. 一.什么是马甲包通过技术手段,多次上架同一款产品的方法. ...

  5. 深入理解PHP 数组之count 函数

    count()PHP count() 函数用于计算数组中的单元数目或对象中的属性个数,返回数组的单元个数或对象中的属性个数.语法:int count( mixed var [, int mode] ) ...

  6. MySQL数据表命令

    显示表的相关信息: show table status like "表名": show table status like "表名" \G       格式化, ...

  7. 20155332 补交ch12课下作业

    20155332 补交ch12课下作业 课下测试提交晚了,我课后补做了一遍,答对13题,答错3题. 试题内容如下所示: 课本内容 1.并发(Concurrency) 访问慢I/O设备:就像当应用程序等 ...

  8. Gitlab+Jenkins学习之路（十三）之发布Java项目到tomcat

    一.新建一台虚拟机安装tomcat ()安装JDK 官网下载jdk:http://www.oracle.com/technetwork/java/javase/downloads/jdk8-downl ...

  9. P3707 [SDOI2017]相关分析

    P3707 [SDOI2017]相关分析 线段树裸题?但是真的很麻烦QAQ 题目给的式子是什么不用管,大力拆开,就是\(\frac{\sum x_iy_i-\overline xy_i-\overli ...

  10. 无监控不运维——使用 Python 写一个小小的项目监控

    在公司里做的一个接口系统,主要是对接第三方的系统接口,所以,这个系统里会和很多其他公司的项目交互.随之而来一个很蛋疼的问题,这么多公司的接口,不同公司接口的稳定性差别很大,访问量大的时候,有的不怎么行 ...