python自动化开发-[第二十三天]-初识爬虫

今日概要：

　　1、爬汽车之家的新闻资讯

　　2、爬github和chouti

　　3、requests和beautifulsoup

　　4、轮询和长轮询

　　5、django request.POST和request.body

一、HTTP知识扫盲

　　1、http的get请求是没有请求体,所有的参数都放在请求头的url里

　　2、http的post请求将请求内容放到请求体里

　　3、http = 请求头+请求体响应头+响应体

　　4、http是无状态请求,一个请求，一次响应就会结束

二、爬取汽车之家的新闻页

#!/usr/bin/python

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

import requests

from bs4 import BeautifulSoup

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

response.encoding = 'gbk' #汽车之家的中文是gbk编码

# print(response.text)

soup = BeautifulSoup(response.text,'html.parser')

tag = soup.find(name='div',attrs={'id':'auto-channel-lazyload-article'})

li_list = tag.find_all('li')

for li in li_list:

    if li.find(name='h3'):

        print(li.find(name='h3').text)

2.1爬取鲜花网

import requests

from bs4 import BeautifulSoup

response = requests.get('http://www.hua.com/aiqingxianhua/')

root = BeautifulSoup(response.text,'html.parser') #实例化soup对象

#通过.进行查找,所有的标签都为对象

div_list = root.find_all(attrs={"class":"grid-item"})

for div in div_list:

    img_dir = div.find(name='img').get('src')

    title = div.find(name='span',attrs={"class":"product-title"})

    price = div.find(name='span',attrs={"class":"price-num"})

    print(img_dir,title.text,price.text)

'''

//img01.hua.com/uploadpic/newpic/9012247.jpg_220x240.jpg 鲜花/幸福的约定-苏醒玫瑰33枝、紫罗兰、银叶菊 339

//img01.hua.com/uploadpic/newpic/9012246.jpg_220x240.jpg 鲜花/邻家女孩-红玫瑰33枝、红色小雏菊 296

//img01.hua.com/uploadpic/newpic/9010011.jpg_220x240.jpg 鲜花/一心一意-玫瑰11枝，粉色勿忘我0.3扎 126

//img01.hua.com/uploadpic/newpic/9012011.jpg_220x240.jpg 鲜花/阳光海岸-19枝香槟玫瑰 218

//img01.hua.com/uploadpic/newpic/9010966.jpg_220x240.jpg 鲜花/一往情深-精品玫瑰礼盒:19枝红玫瑰，勿忘我适量 235

//img01.hua.com/uploadpic/newpic/9012042.jpg_220x240.jpg 鲜花/热恋-红玫瑰50枝 359

//img01.hua.com/uploadpic/newpic/9012041.jpg_220x240.jpg 鲜花/浪漫缤纷-戴安娜粉玫瑰50枝 359

//img01.hua.com/uploadpic/newpic/9012175.jpg_220x240.jpg 鲜花/月光女神-白玫瑰11枝，绿色桔梗5枝，小菊3枝，白色石竹梅4枝 228

//img01.hua.com/uploadpic/newpic/9010947.jpg_220x240.jpg 鲜花/真爱如初-雪山玫瑰11枝、深紫色勿忘我0.3扎 186

//img01.hua.com/uploadpic/newpic/9012177.jpg_220x240.jpg 鲜花/不变的承诺-99枝红玫瑰 519

'''

三、爬取gitlab和chouti的新闻页

github自动登录

#!/usr/bin/python

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

import requests

from bs4 import BeautifulSoup

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

b1 = BeautifulSoup(r1.text,'html.parser')

auth_token = b1.find(attrs={'name':'authenticity_token'}).get('value')

r1_cookies_data = r1.cookies.get_dict()

print(auth_token)

r2 = requests.post('https://github.com/session', data={

    "commit": "Sign in",

    "utf8": '✓',

    "authenticity_token": auth_token,

    "login": "xxxx",

    "password": "xxxx",

},

                   cookies=r1_cookies_data)

r2_cookies_data  = r2.cookies.get_dict()

print(r1_cookies_data)

print(r2_cookies_data)

all_cookies = {}

all_cookies.update(r1_cookies_data)

all_cookies.update(r2_cookies_data)

#github直接用带token之后的cookies就行

r3 = requests.get('https://github.com/settings/emails',cookies=r2_cookies_data)

print(r3.text)

登录抽屉并自动点赞

#!/usr/bin/python

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

import requests

r1 = requests.get(url='http://dig.chouti.com/')

r1_cookies_data = r1.cookies.get_dict()

r2 = requests.post('http://dig.chouti.com/login',data={'phone':'xxx',"password":"xxx","oneMonth":1}

                   ,cookies=r1_cookies_data)

r2_cookies_data  = r2.cookies.get_dict()

print(r1_cookies_data)

print(r2_cookies_data)

all_cookies = {}

all_cookies.update(r1_cookies_data)

all_cookies.update(r2_cookies_data)

'''

session_id 在第一次请求

{'JSESSIONID': 'aaaIZQdBA4siraQ2m0t8v', 'route': '0c5178ac241ad1c9437c2aafd89a0e50', 'gpsd': 'dd55c4cda0a45f6bc3274a79a7e50316'}

{'puid': '417d102e3c72e88cd6003bc984c569b4', 'gpid': '4c91ec17bd8340bdb75116916e19bc20'}

'''

r3 = requests.post('http://dig.chouti.com/link/vote?linksId=14708906',cookies=r1_cookies_data)

print(r3.text)

'''

{"result":{"code":"9999", "message":"推荐成功", "data":{"jid":"cdu_50096919787","likedTime":"1508043437615000","lvCount":"6","nick":"congratula","uvCount":"3","voteTime":"小于1分钟前"}}}

'''

注意:有的登录页面,登录的时候不一定会给cookie,需要get一次才给cookie,而登录的时候仅仅是授权,get的时候的cookie,这样就不需要带第二次的cookie去请求

四、轮询和长轮询　　

轮询：客户端定时向服务器发送Ajax请求，服务器接到请求后马上返回响应信息并关闭连接。
优点：后端程序编写比较容易。
缺点：请求中有大半是无用，浪费带宽和服务器资源。
实例：适于小型应用。
长轮询：客户端向服务器发送Ajax请求，服务器接到请求后hold住连接，直到有新消息才返回响应信息并关闭连接，客户端处理完响应信息后再向服务器发送新的请求，服务器端会设置超时时间,当出现超时的时候，服务端会断开链接，客户端会再次请求服务端hold住
优点：在无消息的情况下不会频繁的请求。
缺点：服务器hold连接会消耗资源。
实例：WebQQ、Hi网页版、Facebook IM。

　　另外，对于长连接和socket连接也有区分：

长连接：在页面里嵌入一个隐蔵iframe，将这个隐蔵iframe的src属性设为对一个长连接的请求，服务器端就能源源不断地往客户端输入数据。
优点：消息即时到达，不发无用请求。
缺点：服务器维护一个长连接会增加开销。
实例：Gmail聊天

五、requests的用法

　　1、GET请求：　　　　

requests.get(url="http://www.oldboyedu.com")

# data="http GET / http1.1\r\nhost:oldboyedu.com\r\n....\r\n\r\n"

requests.get(url="http://www.oldboyedu.com/index.html?p=1")

# data="http GET /index.html?p=1 http1.1\r\nhost:oldboyedu.com\r\n....\r\n\r\n"

requests.get(url="http://www.oldboyedu.com/index.html",params={'p':1})

# data="http GET /index.html?p=1 http1.1\r\nhost:oldboyedu.com\r\n....\r\n\r\n"

　　2、POST请求：

requests.post(url="http://www.oldboyedu.com",data={'name':'alex','age':18}) # 默认请求头：application/x-www-form-urlencoded

data="http POST / http1.1\r\nhost:oldboyedu.com\r\n....\r\n\r\nname=alex&age=18"

requests.post(url="http://www.oldboyedu.com",json={'name':'alex','age':18}) # 默认请求头：application/json

data="http POST / http1.1\r\nhost:oldboyedu.com\r\n....\r\n\r\n{"name": "alex", "age": 18}"

requests.post(

	url="http://www.oldboyedu.com",

	params={'p':1},

	json={'name':'alex','age':18}

) # 默认请求头：application/json

data="http POST /?p=1 http1.1\r\nhost:oldboyedu.com\r\n....\r\n\r\n{"name": "alex", "age": 18}"

　3、更多参数

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

更多参数

　　verify一般和cert合着用

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'))

    # } #元祖里套元祖

    # 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

    #一些非form表单，浏览器自带的认证框,它们都是通过固定的算法得出来的,可以用这个去认证

    #r.headers['Authorization'] = _basic_auth_str(self.username, self.password) 查看源码

    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():

    # 设置超时时间

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

    # print(ret)

    # 设置超时时间和断开时间

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

    # print(ret)

    pass

def param_allow_redirects():

    #比如访问一个网站redirect另外一个地址,这次http请求是有返回值的,allow_redirects可以设置是否跳转到新的地址,重新发请求

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

    print(ret.text)

def param_proxies():

    # 设置代理,可以设置很多

    # 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

    # 设置需要认证的代理

    #

    # 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():

    #将一个大的数据比如30g,进行分段传输

    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():

    #建议刚开始 别使用,能记录cookie等内容 不必每次都去 取

    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': "8615131255089",

            'password': "xxxxxx",

            'oneMonth': ""

        }

    )

    i3 = session.post(

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

    )

    print(i3.text)

六、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。

　　　　soup = BeautifulSoup(html_doc, features="lxml") #会以xml格式解析,需要额外安装lxml，比html.parser节省资源

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，标签名称

# tag = soup.find('a')

# name = tag.name # 获取

# print(name)

# tag.name = 'span' # 设置

# print(soup)

　　2. attr，标签属性

# tag = soup.find('a')

# attrs = tag.attrs    # 获取 结果是一个集合

# print(attrs)

# tag.attrs = {'ik':123} # 设置

# tag.attrs['id'] = 'iiiii' # 设置

# print(soup)

　　3. children,所有子标签

# body = soup.find('body')

# v = body.children

　　4. children,所有子子孙孙标签

# 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）

# tag = soup.find('body')

# tag.clear()

# print(soup)

　　6. decompose,递归的删除所有的标签,(自己也会删除)

# 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(类似于dict里的pop)

# 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） (将标签对象转换为格式)

# 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）

# 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

# 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 class是类变量可以用class_ 去代替

# 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

# tag = soup.find('a')

# v = tag.has_attr('id')

# print(v)

　　13. get_text,获取标签内部文本内容

html_doc = """

<html><head><title>The Dormouse's story</title></head>

<body>

    <a id='a1'>123</a>

</body>

</html>

"""

soup = BeautifulSoup(html_doc, features="lxml")

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

# 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'

# tag = soup.find('br')

# v = tag.is_empty_element

# print(v)

　　16. 当前的关联标签

#from bs4.element import  Tag

# soup.next #查该标签内部子代

# soup.next_element

# soup.next_elements #递归查找子代

# soup.next_sibling

# soup.next_siblings #只查下面的

#

# tag.previous #查标签外部

# tag.previous_element

# tag.previous_elements

# tag.previous_sibling #查兄弟标签

# tag.previous_siblings #只向上查找

#

# tag.parent #查父亲

# tag.parents

　　17. 查找某标签的关联标签

# tag.find_next(...)  #可以加条件筛选

# 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

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

# 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)

　　string和text的区别:

　　　　1.string 可以赋值，text不可以

2.string 这个类型<class 'bs4.element.NavigableString'> text是这个类型 <class 'str'>

　　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)

　　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)

　　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)

　　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)

　 24. 创建标签之间的关系(非常规思维,创建的关系在soup里是无法看到的)

# 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

# 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

# tag = soup.find('a')

# v = tag.unwrap()

# print(soup)

爬取知乎：