爬蟲基礎——request模塊和BeautifulSoup模塊

文章來自這裏

   request

Python標準庫中提供了：urllib、urllib二、httplib等模塊以供Http請求，可是，它的 API 太渣了。它是爲另外一個時代、另外一個互聯網所建立的。它須要巨量的工做，甚至包括各類方法覆蓋，來完成最簡單的任務。

Requests 是使用 Apache2 Licensed 許可證的 基於Python開發的HTTP 庫，其在Python內置模塊的基礎上進行了高度的封裝，從而使得Pythoner進行網絡請求時，變得美好了許多，使用Requests能夠垂手可得的完成瀏覽器可有的任何操做。

一、GET請求

# 一、無參數實例
  
import requests
  
ret = requests.get('https://github.com/timeline.json')
  
print ret.url
print ret.text
  
  
  
# 二、有參數實例
  
import requests
  
payload = {'key1': 'value1', 'key2': 'value2'}
ret = requests.get("http://httpbin.org/get", params=payload)
  
print ret.url
print ret.text

二、POST請求

# 一、基本POST實例
  
import requests
  
payload = {'key1': 'value1', 'key2': 'value2'}
ret = requests.post("http://httpbin.org/post", data=payload)
  
print ret.text
  
  
# 二、發送請求頭和數據實例
  
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

# 若是有中文 payload = {'name': '王陽'，'age': 24}， 則
# ret = requests.post(
#　　　　　　　　　　　　url, 
#　　　　　　　　　　　　data=json.dumps(payload，ensure_ascii=False).encode(encoding="utf-8"), # 變成二進制才能解析中文
#　　　　　　　　　　　　headers={'content-type': 'application/json'})

# 請求體： k1=v1&k2=v2&k3=v3   請求頭：Content-Type: application/x-www-form-urlencoded

# 請求體: "{'name': 'sam', 'age': 23}" (即字符串類型或字節類型)   請求體：Content-Type: application/json

三、其餘請求

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礎上構建
requests.request(method, url, **kwargs)

 四、更多參數

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]>
    """

參數列表

更多參數

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():
    # - 能夠是字典
    # - 能夠是字符串
    # - 能夠是字節（ascii編碼之內）

    # requests.request(method='get',
    # url='http://127.0.0.1:8000/test/',
    # params={'k1': 'v1', 'k2': '水電費'})

    # requests.request(method='get',
    # url='http://127.0.0.1:8000/test/',
    # params="k1=v1&k2=水電費&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'))

    # 錯誤
    # requests.request(method='get',
    # url='http://127.0.0.1:8000/test/',
    # params=bytes("k1=v1&k2=水電費&k3=v3&k3=vv3", encoding='utf8'))
    pass


def param_data():
    # 能夠是字典
    # 能夠是字符串
    # 能夠是字節
    # 能夠是文件對象

    # requests.request(method='POST',
    # url='http://127.0.0.1:8000/test/',
    # data={'k1': 'v1', 'k2': '水電費'})

    # 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'), # 文件內容是：k1=v1;k2=v2;k3=v3;k3=v4
    # headers={'Content-Type': 'application/x-www-form-urlencoded'}
    # )
    pass


def param_json():
    # 將json中對應的數據進行序列化成一個字符串，json.dumps(...)
    # 而後發送到服務器端的body中，而且Content-Type是 {'Content-Type': 'application/json'}
    requests.request(method='POST',
                     url='http://127.0.0.1:8000/test/',
                     json={'k1': 'v1', 'k2': '水電費'})


def param_headers():
    # 發送請求頭到服務器端
    requests.request(method='POST',
                     url='http://127.0.0.1:8000/test/',
                     json={'k1': 'v1', 'k2': '水電費'},
                     headers={'Content-Type': 'application/x-www-form-urlencoded'}
                     )


def param_cookies():
    # 發送Cookie到服務器端
    requests.request(method='POST',
                     url='http://127.0.0.1:8000/test/',
                     data={'k1': 'v1', 'k2': 'v2'},
                     cookies={'cook1': 'value1'},
                     )
    # 也能夠使用CookieJar（字典形式就是在此基礎上封裝）
    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():
    # 發送文件
    # file_dict = {
    # 'f1': open('readme', 'rb')
    # }
    # requests.request(method='POST',
    # url='http://127.0.0.1:8000/test/',
    # files=file_dict)

    # 發送文件，定製文件名
    # file_dict = {
    # 'f1': ('test.txt', open('readme', 'rb'))
    # }
    # requests.request(method='POST',
    # url='http://127.0.0.1:8000/test/',
    # files=file_dict)

    # 發送文件，定製文件名
    # file_dict = {
    # 'f1': ('test.txt', "hahsfaksfa9kasdjflaksdjf")
    # }
    # requests.request(method='POST',
    # url='http://127.0.0.1:8000/test/',
    # files=file_dict)

    # 發送文件，定製文件名
    # 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:
    # # 在此處理響應。
    # for i in r.iter_content():
    # print(i)


def requests_session():
    import requests

    session = requests.Session()

    ### 一、首先登錄任何頁面，獲取cookie

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

    ### 二、用戶登錄，攜帶上一次的cookie，後臺對cookie中的 gpsd 進行受權
    i2 = session.post(
        url="http://dig.chouti.com/login",
        data={
            'phone': "8615131255089",
            'password': "xxxxxx",
            'oneMonth': ""
        }
    )

    i3 = session.post(
        url="http://dig.chouti.com/link/vote?linksId=8589623",
    )
    print(i3.text)

參數示例

參數示例

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

   BeautifulSoup

BeautifulSoup是一個模塊，該模塊用於接收一個HTML或XML字符串，而後將其進行格式化，以後遍能夠使用他提供的方法進行快速查找指定元素，從而使得在HTML或XML中查找指定元素變得簡單。

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總共</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")
# 找到第一個a標籤
tag1 = soup.find(name='a')
# 找到全部的a標籤
tag2 = soup.find_all(name='a')
# 找到id＝link2的標籤
tag3 = soup.select('#link2')

 安裝：

pip3 install beautifulsoup4

 

使用示例：

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，標籤名稱

# tag = soup.find('a')
# name = tag.name # 獲取
# print(name)
# tag.name = 'span' # 設置
# print(soup)

2. attr，標籤屬性

# tag = soup.find('a')
# attrs = tag.attrs    # 獲取
# print(attrs)
# tag.attrs = {'ik':123} # 設置
# tag.attrs['id'] = 'iiiii' # 設置
# print(soup)

3. children,全部子標籤

# body = soup.find('body')
# v = body.children

4. children,全部子子孫孫標籤

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

5. clear,將標籤的全部子標籤所有清空（保留標籤名）

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

6. decompose,遞歸的刪除全部的標籤

# body = soup.find('body')
# body.decompose()
# print(soup)

7. extract,遞歸的刪除全部的標籤，並獲取刪除的標籤

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

8. decode,轉換爲字符串（含當前標籤）；decode_contents（不含當前標籤）

# body = soup.find('body')
# v = body.decode()
# v = body.decode_contents()
# print(v)

9. encode,轉換爲字節（含當前標籤）；encode_contents（不含當前標籤）

# body = soup.find('body')
# v = body.encode()
# v = body.encode_contents()
# print(v)

10. find,獲取匹配的第一個標籤

# 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,獲取匹配的全部標籤

# 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)
 
# ####### 正則 #######
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)
 
# ####### 方法篩選 #######
# def func(tag):
# return tag.has_attr('class') and tag.has_attr('id')
# v = soup.find_all(name=func)
# print(v)
 
 
# ## get,獲取標籤屬性
# tag = soup.find('a')
# v = tag.get('id')
# print(v)

12. has_attr,檢查標籤是否具備該屬性

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

13. get_text,獲取標籤內部文本內容

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

14. index,檢查標籤在某標籤中的索引位置

# 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)

15. is_empty_element,是不是空標籤(是否能夠是空)或者自閉合標籤，

     判斷是不是以下標籤：'br' , 'hr', 'input', 'img', 'meta','spacer', 'link', 'frame', 'base'

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

16. 當前的關聯標籤

# 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. 查找某標籤的關聯標籤

# 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(...)
 
# 參數同find_all

18. select,select_one, CSS選擇器

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)

19. 標籤的內容

# tag = soup.find('span')
# print(tag.string)          # 獲取
# tag.string = 'new content' # 設置
# print(soup)
 
# tag = soup.find('body')
# print(tag.string)
# tag.string = 'xxx'
# print(soup)
 
# tag = soup.find('body')
# v = tag.stripped_strings  # 遞歸內部獲取全部標籤的文本
# print(v)

20.append在當前標籤內部追加一個標籤

# 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 = '我是一個新來的'
# tag = soup.find('body')
# tag.append(obj)
# print(soup)

21.insert在當前標籤內部指定位置插入一個標籤

# from bs4.element import Tag
# obj = Tag(name='i', attrs={'id': 'it'})
# obj.string = '我是一個新來的'
# tag = soup.find('body')
# tag.insert(2, obj)
# print(soup)

22. insert_after,insert_before 在當前標籤後面或前面插入

# from bs4.element import Tag
# obj = Tag(name='i', attrs={'id': 'it'})
# obj.string = '我是一個新來的'
# tag = soup.find('body')
# # tag.insert_before(obj)
# tag.insert_after(obj)
# print(soup)

23. replace_with 在當前標籤替換爲指定標籤

# from bs4.element import Tag
# obj = Tag(name='i', attrs={'id': 'it'})
# obj.string = '我是一個新來的'
# tag = soup.find('div')
# tag.replace_with(obj)
# print(soup)

24. 建立標籤之間的關係

# tag = soup.find('div')
# a = soup.find('a')
# tag.setup(previous_sibling=a)
# print(tag.previous_sibling)

25. wrap，將指定標籤把當前標籤包裹起來

# from bs4.element import Tag
# obj1 = Tag(name='div', attrs={'id': 'it'})
# obj1.string = '我是一個新來的'
#
# tag = soup.find('a')
# v = tag.wrap(obj1)
# print(soup)
 
# tag = soup.find('a')
# v = tag.wrap(soup.find('p'))
# print(soup)

26. unwrap，去掉當前標籤，將保留其包裹的標籤

# tag = soup.find('a')
# v = tag.unwrap()
# print(soup)

更多參數官方：http://beautifulsoup.readthedocs.io/zh_CN/v4.4.0/