（第一篇）爬虫技术专栏之requests模块与BeautifulSoup模块

自从大一开始就想在博客专门建立一个分类，深度总结一下爬虫技术相关的东西，但是一直拖到现在。大二马上要结束了，准备从暑假开始认真总结，每一篇文章都争取带一个小案例。给学弟们作参考用~

0x01 requests模块

requests是一个作为 Python 构建的优雅而简单的HTTP库。目前它使用了Apache2 Licensed许可证，requests在Python一些基本库上进行了高度封装。中文文档： http://docs.python-requests.org/zh_CN/latest/

0x001 安装

pip install requests

0x002 常用方法

• requests.get(url, params=None, **kwargs)

# 发送一个get请求到服务器端
# url接收一个URL地址
# parmas接收一个字典对象
# 返回一个请求对象

• requests.options(url, **kwargs)

# 发送一个options请求到服务器端
# url接收一个URL地址

• requests.head(url, **kwargs)

# 发送一个head请求到服务器端
# url接收一个URL地址

• requests.post(url, data=None, json=None, **kwargs)

# 发送一个post请求到服务器端
# url接收一个URL地址
# data接收一个字典、字节或者是一个文件对象
# json接收一个json数据

• requests.put(url, data=None, **kwargs)

# 发送一个put请求到服务器端
# url接收一个URL地址
# data接收一个字典、字节或者是一个文件对象

• requests.patch(url, data=None, **kwargs)

# 发送一个patch请求到服务器端
# url接收一个URL地址
# data接收一个字典、字节或者是文件对象

• requests.delete(url, **kwargs)

# 发送一个delete请求到服务器端
# url接收一个URL地址

• requests.request(method, url, **kwargs)

# 发送一个请求
# method指定请求的方法
# url接收一个URL地址
# params接收一个字典、字节或者是文件对象
# data接收一个使用元组构成的列表[(key, value)]或者是字典、字节或者是文件对象
# json接收一个json数据
# headers接收一个字典，用于构成请求头
# cookies接收一个cookie对象
# files接收一个文件对象
# auth接收一个元组，用来身份认证
# timeout接收一个浮点数或者是元组
# allow_redirects接收一个布尔值，默认是True，是否开启重定向
# proxies 接收代理的url
# verify 是否启用安全认证
# stream 是否使用数据流的方式传输文件
# cert 使用证书文件，如果是pem文件，则(xxx.pem)，如果是crt文件和key文件，则('xxx.crt', 'xxx.key')

0x003 requests.api源码

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

"""
requests.api

This module implements the Requests API.

:copyright: (c) 2012 by Kenneth Reitz.
:license: Apache2, see LICENSE for more details.
"""

from . import sessions

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, list of tuples or bytes to send
        in the body of the :class:`Request`.
    :param data: (optional) Dictionary, list of tuples, bytes, or file-like
        object to send in the body of the :class:`Request`.
    :param json: (optional) A JSON serializable Python object 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 many seconds 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. Enable/disable GET/OPTIONS/POST/PUT/PATCH/DELETE/HEAD redirection. Defaults to ``True``.
    :type allow_redirects: bool
    :param proxies: (optional) Dictionary mapping protocol to the URL of the proxy.
    :param verify: (optional) Either a boolean, in which case it controls whether we verify
            the server's TLS certificate, or a string, in which case it must be a path
            to a CA bundle to use. 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', 'https://httpbin.org/get')
      <Response [200]>
    """

    # By using the 'with' statement we are sure the session is closed, thus we
    # avoid leaving sockets open which can trigger a ResourceWarning in some
    # cases, and look like a memory leak in others.
    with sessions.Session() as session:
        return session.request(method=method, url=url, **kwargs)

def get(url, params=None, **kwargs):
    r"""Sends a GET request.

    :param url: URL for the new :class:`Request` object.
    :param params: (optional) Dictionary, list of tuples or bytes to send
        in the body of the :class:`Request`.
    :param \*\*kwargs: Optional arguments that ``request`` takes.
    :return: :class:`Response <Response>` object
    :rtype: requests.Response
    """

    kwargs.setdefault('allow_redirects', True)
    return request('get', url, params=params, **kwargs)

def options(url, **kwargs):
    r"""Sends an OPTIONS request.

    :param url: URL for the new :class:`Request` object.
    :param \*\*kwargs: Optional arguments that ``request`` takes.
    :return: :class:`Response <Response>` object
    :rtype: requests.Response
    """

    kwargs.setdefault('allow_redirects', True)
    return request('options', url, **kwargs)

def head(url, **kwargs):
    r"""Sends a HEAD request.

    :param url: URL for the new :class:`Request` object.
    :param \*\*kwargs: Optional arguments that ``request`` takes.
    :return: :class:`Response <Response>` object
    :rtype: requests.Response
    """

    kwargs.setdefault('allow_redirects', False)
    return request('head', url, **kwargs)

def post(url, data=None, json=None, **kwargs):
    r"""Sends a POST request.

    :param url: URL for the new :class:`Request` object.
    :param data: (optional) Dictionary, list of tuples, 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 \*\*kwargs: Optional arguments that ``request`` takes.
    :return: :class:`Response <Response>` object
    :rtype: requests.Response
    """

    return request('post', url, data=data, json=json, **kwargs)

def put(url, data=None, **kwargs):
    r"""Sends a PUT request.

    :param url: URL for the new :class:`Request` object.
    :param data: (optional) Dictionary, list of tuples, 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 \*\*kwargs: Optional arguments that ``request`` takes.
    :return: :class:`Response <Response>` object
    :rtype: requests.Response
    """

    return request('put', url, data=data, **kwargs)

def patch(url, data=None, **kwargs):
    r"""Sends a PATCH request.

    :param url: URL for the new :class:`Request` object.
    :param data: (optional) Dictionary, list of tuples, 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 \*\*kwargs: Optional arguments that ``request`` takes.
    :return: :class:`Response <Response>` object
    :rtype: requests.Response
    """

    return request('patch', url, data=data, **kwargs)

def delete(url, **kwargs):
    r"""Sends a DELETE request.

    :param url: URL for the new :class:`Request` object.
    :param \*\*kwargs: Optional arguments that ``request`` takes.
    :return: :class:`Response <Response>` object
    :rtype: requests.Response
    """

    return request('delete', url, **kwargs)

0x02 BeautifulSoup模块

Beautiful Soup是一个用于从HTML和XML文件中提取数据的Python库。它能够通过你喜欢的转换器实现惯用的文档导航,查找,修改文档的方式.Beautiful Soup会帮你节省数小时甚至数天的工作时间。中文文档： https://www.crummy.com/software/BeautifulSoup/bs4/doc.zh/

0x001安装

• Debain或Ubuntu

apt-get install Python-bs4

• easy_install和pip安装，兼容Python2.x和Python3.x

easy_install beautifulsoup4
pip install beautifulsoup4

• 源码安装

下载地址：https://www.crummy.com/software/BeautifulSoup/bs4/download/4.0/
首先解压下载的源码压缩包，进入源码目录，执行：python setup.py install

• 安装解析器lxml和html5lib

apt-get install Python-lxml
easy_install lxml
pip install lxml
apt-get install Python-html5lib
easy_install html5lib
pip install html5lib

从上表可知，推荐使用lxml解析器效率更高，但是xml或html文档的格式不正确的话返回的结果可能不正确。

from bs4 import BeautifulSoup
soup = BeautifulSoup(open("index.html"))  # 直接打开本地html文件
soup = BeautifulSoup("<html>data</html>")  #传入html文本

0x002 常用对象介绍

Beautiful Soup将HTML或XML文件转换为树形结构，每个节点都是Python对象。总共可以分为四种：

• 标签对象

  tag = soup.b
  tag.name
  tag.attrs
  

• 可遍历的字符串NavigableString对象

  1. 由于字符串包含在了Tag内，所以Beautiful Soup用 NavigableString 类来包装tag中的字符串。
  2. tag.string：它的类型是BS的字符串，可以通过 unicode() 方法将其转换为Unicode字符串。 unicode_string = unicode(tag.string)
  3. BS的Tag中包含的字符串不可以被编辑，但是可以通过 replace_with() 方法被替换成为其他的字符串。

• BeautifulSoup对象

  1. 该对象表示的全部的内容。其 soup.name 属性的值是： u'[document]' 。

• 注释及特殊字符串Comment对象

  1. Comment 对象是一个特殊类型的 NavigableString 对象

     markup = "<b><!--Hey, buddy. Want to buy a used parser?--></b>"
     soup = BeautifulSoup(markup)
     comment = soup.b.string
     type(comment)
     # <class 'bs4.element.Comment'>
     print(soup.b.prettify())   # 输出成为了特殊的格式
     # <b>
     #  <!--Hey, buddy. Want to buy a used parser?-->
     # </b>

  2. Beautiful Soup定义的其他类型可能会出现在XML文档中，CData、ProcessingInstruction、Declaration、Doctype，这些类型与Comment类似，都是NavigableString的子类，只是添加了一些特殊的方法。

0x003 常用属性和方法

0x004 官方示例

def has_class_but_no_id(tag):
    return tag.has_attr('class') and not tag.has_attr('id')

soup.find_all(has_class_but_no_id)
tag.find_all(Key=’Value)                               # 搜索所有Key的值是Value的标签
soup.find_all(Key=re.compile("RegExp"), Key='Value')   # 结合正则表达式使用并且是或的逻辑关系
tag.find_all(text=’xxx’)                               # 使用text参数可以搜索文档中的字符串内容
tag.find_all(text=[‘xxx’, ‘xxx’, ])                    # text参数可以接受字符串、正则、列表和布尔值
tag.find_all(‘TagName’, limit=Number)                  # 返回Number个符合的标签
tag.find_all(‘TagName’, recursive=True/False)          # 是否只匹配直接子节点
tag.find( name , attrs , recursive , text , **kwargs ) # 直接返回一个结果，匹配不到时返回None，而find_all()返回空列表[]
# 类似的方法还有：
tag.find_parents()
tag.find_parent()
tag.find_next_siblings()
tag.find_next_sibling()
tag.find_previous_siblings()
tag.find_previous_sibling()
tag.find_all_next()
tag.find_next()
tag.find_all_previous()
tag.find_previous()
# Beautiful Soup支持大部分的CSS选择器，即tag.select():
tag.append(“Content”)                                 # 向标签中添加内容
tag.new_string()                                      # 创建新的字符串对象
tag.new_tag()                                         # 创建新的标签对象
tag.insert()                                          # 插入标签对象
tag.insert_before()                                   # 在tag标签之前插入新的标签对象
tag.insert_after()                                    # 在tag标签之后插入新的标签对象
tag. clear()                                          # 清除当前tag的内容
tag. extract()                                        # 将当前的tag从文档树中删除，并且返回该tag对象
tag. decompose()                                      # 从当前的文档树中移除，并且完全销毁该tag对象
tag. replace_with()                                   # 替换该tag对象
tag. wrap()                                           # 用传入的tag对象包装指定的tag对象
tag. unwrap()                                         # 取消使用上层tag对象的包装，并返回被移除的上层tag对象
tag. prettify()                                       # 将文档树格式化后使用Unicode编码输出
tag. get_text()                                       # 获取tag对象中的内容

0x005 自动登录GitHub

# -*- coding:utf8 -*-

import requests
from bs4 import BeautifulSoup

# 用户名和密码
username = 'xxx'
password = 'xxx'

# 请求头
header = {
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
    'Accept-Encoding': 'gzip, deflate, br',
    'Accept-Language': 'zh-CN,zh;q=0.9',
    'Connection': 'keep-alive',
    'Host': 'github.com',
    'Referer': "https://github.com/xvGe/xvGe.github.io",
    'Upgrade-Insecure-Requests': '1',
    'User-Agent': "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36",
}

# 登录
response = requests.request('get', 'https://github.com/login', headers=header)
soup = BeautifulSoup(response.text, features='lxml')

# 获取登录token
token = soup.find(name='input', attrs={'name': "authenticity_token"})['value']

# 获取cookie
cookie = response.cookies.get_dict()

# 提交的登录数据
formData = {
    'commit': 'Sign in',
    'utf8': '✓',
    'authenticity_token': token,
    'login': username,
    'password': password,

}

# 提交登录数据
response = requests.request('post', 'https://github.com/session', data=formData, cookies=cookie, headers=header)

response.close()