（第一篇）爬蟲技術專欄之requests模塊與BeautifulSoup模塊

自從大一開始就想在博客專門建立一個分類，深度總結一下爬蟲技術相關的東西，但是一直拖到現在。大二馬上要結束了，準備從暑假開始認真總結，每一篇文章都爭取帶一個小案例。給學弟們作參考用~

0x01 requests模塊

requests是一個作為Python構建的優雅而簡單的HTTP庫。目前它使用了Apache2 Licensed許可證，requests在Python一些基本庫上進行了高度封裝。中文文檔：http://docs.python-requests.org/zh_CN/latest/

0x001 安裝

pip install requests

0x002 常用方法

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

# 發送一個get請求到服務器端
# url接收一個URL地址
# parmas接收一個字典對象
# 返回一個請求對象

• requests.options(url, **kwargs)

# 發送一個options請求到服務器端
# url接收一個URL地址

• requests.head(url, **kwargs)

# 發送一個head請求到服務器端
# url接收一個URL地址

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

# 發送一個post請求到服務器端
# url接收一個URL地址
# data接收一個字典、字節或者是一個文件對象
# json接收一個json數據

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

# 發送一個put請求到服務器端
# url接收一個URL地址
# data接收一個字典、字節或者是一個文件對象

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

# 發送一個patch請求到服務器端
# url接收一個URL地址
# data接收一個字典、字節或者是文件對象

• requests.delete(url, **kwargs)

# 發送一個delete請求到服務器端
# url接收一個URL地址

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

# 發送一個請求
# method指定請求的方法
# url接收一個URL地址
# params接收一個字典、字節或者是文件對象
# data接收一個使用元組構成的列表[(key, value)]或者是字典、字節或者是文件對象
# json接收一個json數據
# headers接收一個字典，用于構成請求頭
# cookies接收一個cookie對象
# files接收一個文件對象
# auth接收一個元組，用來身份認證
# timeout接收一個浮點數或者是元組
# allow_redirects接收一個布爾值，默認是True，是否開啟重定向
# proxies 接收代理的url
# verify 是否啟用安全認證
# stream 是否使用數據流的方式傳輸文件
# cert 使用證書文件，如果是pem文件，則(xxx.pem)，如果是crt文件和key文件，則('xxx.crt', 'xxx.key')

0x003 requests.api源碼

# -*- 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模塊

Beautiful Soup是一個用于從HTML和XML文件中提取數據的Python庫。它能夠通過你喜歡的轉換器實現慣用的文檔導航,查找,修改文檔的方式.Beautiful Soup會幫你節省數小時甚至數天的工作時間。中文文檔：https://www.crummy.com/software/BeautifulSoup/bs4/doc.zh/

0x001安裝

• Debain或Ubuntu

apt-get install Python-bs4

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

easy_install beautifulsoup4
pip install beautifulsoup4

• 源碼安裝

下載地址：https://www.crummy.com/software/BeautifulSoup/bs4/download/4.0/
首先解壓下載的源碼壓縮包，進入源碼目錄，執行：python setup.py install

• 安裝解析器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

從上表可知，推薦使用lxml解析器效率更高，但是xml或html文檔的格式不正確的話返回的結果可能不正確。

from bs4 import BeautifulSoup
soup = BeautifulSoup(open("index.html"))  # 直接打開本地html文件
soup = BeautifulSoup("<html>data</html>")  #傳入html文本

0x002 常用對象介紹

Beautiful Soup將HTML或XML文件轉換為樹形結構，每個節點都是Python對象。總共可以分為四種：

• 標簽對象

  1. Tag對象與原生的HTML或XML對象相同。tag = soup.b
  2. Name是Tag的名字。tag.name
  3. Attrs, Tag的屬性是個列表，可以使用tag[‘class’]的方式操作屬性，也可以使用tag.attrs來操作屬性。

• 可遍歷的字符串NavigableString對象

  1. 由于字符串包含在了Tag內，所以Beautiful Soup用 NavigableString 類來包裝tag中的字符串。
  2. tag.string：它的類型是BS的字符串，可以通過unicode()方法將其轉換為Unicode字符串。unicode_string = unicode(tag.string)
  3. BS的Tag中包含的字符串不可以被編輯，但是可以通過replace_with()方法被替換成為其他的字符串。

• BeautifulSoup對象

  1. 該對象表示的全部的內容。其soup.name屬性的值是：u'[document]'。

• 注釋及特殊字符串Comment對象

  1. Comment 對象是一個特殊類型的 NavigableString 對象

     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())   # 輸出成為了特殊的格式
     # <b>
     #  <!--Hey, buddy. Want to buy a used parser?-->
     # </b>

  2. Beautiful Soup定義的其他類型可能會出現在XML文檔中，CData、ProcessingInstruction、Declaration、Doctype，這些類型與Comment類似，都是NavigableString的子類，只是添加了一些特殊的方法。

0x003 常用屬性和方法

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的標簽
soup.find_all(Key=re.compile("RegExp"), Key='Value')   # 結合正則表達式使用并且是或的邏輯關系
tag.find_all(text=’xxx’)                               # 使用text參數可以搜索文檔中的字符串內容
tag.find_all(text=[‘xxx’, ‘xxx’, ])                    # text參數可以接受字符串、正則、列表和布爾值
tag.find_all(‘TagName’, limit=Number)                  # 返回Number個符合的標簽
tag.find_all(‘TagName’, recursive=True/False)          # 是否只匹配直接子節點
tag.find( name , attrs , recursive , text , **kwargs ) # 直接返回一個結果，匹配不到時返回None，而find_all()返回空列表[]
# 類似的方法還有：
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選擇器，即tag.select():
tag.append(“Content”)                                 # 向標簽中添加內容
tag.new_string()                                      # 創建新的字符串對象
tag.new_tag()                                         # 創建新的標簽對象
tag.insert()                                          # 插入標簽對象
tag.insert_before()                                   # 在tag標簽之前插入新的標簽對象
tag.insert_after()                                    # 在tag標簽之后插入新的標簽對象
tag. clear()                                          # 清除當前tag的內容
tag. extract()                                        # 將當前的tag從文檔樹中刪除，并且返回該tag對象
tag. decompose()                                      # 從當前的文檔樹中移除，并且完全銷毀該tag對象
tag. replace_with()                                   # 替換該tag對象
tag. wrap()                                           # 用傳入的tag對象包裝指定的tag對象
tag. unwrap()                                         # 取消使用上層tag對象的包裝，并返回被移除的上層tag對象
tag. prettify()                                       # 將文檔樹格式化后使用Unicode編碼輸出
tag. get_text()                                       # 獲取tag對象中的內容

0x005 自動登錄GitHub

# -*- coding:utf8 -*-

import requests
from bs4 import BeautifulSoup

# 用戶名和密碼
username = 'xxx'
password = 'xxx'

# 請求頭
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",
}

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

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

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

# 提交的登錄數據
formData = {
    'commit': 'Sign in',
    'utf8': '?',
    'authenticity_token': token,
    'login': username,
    'password': password,

}

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

response.close()