目录
python中的爬虫，有两个特别方便的模块，requests模块以及BeautifulSoup模块，requests模块主要提供http访问，BeautifulSoup模块主要解决爬取页面后对页面标签以及内容的处理。
例子：爬取汽车之家的新闻
先看个例子热热身：
#!/usr/bin/python
# -*- coding:utf-8 -*-
import requests
response = requests.get('http://www.autohome.com.cn/news/')
# print(response.content) # 字节
response.encoding = 'gbk'
html = response.text # 字符串
# 字符串结构化成为特殊的数据结构
from bs4 import BeautifulSoup
obj = BeautifulSoup(html,'html.parser')
# 找到符合条件的第一个标签
tag = obj.find(name='div',id='auto-channel-lazyload-article')
# 列表类型【标签对象,标签对象,标签对象,标签对象,标签对象,】
li_list = tag.find_all(name='li')
for item in li_list:
h3_obj = item.find(name='h3')
p_obj = item.find(name='p')
a_obj = item.find(name='a')
if h3_obj:
print(h3_obj.text)
print(p_obj.text)
print(a_obj.attrs.get('href'))
例子二：对于需要登录的页面进行的页面爬取
例子中是需要对github页面爬取处理的思路：
# 用户登录后才能查看的页面 https://github.com/settings/repositories
"""
实例二：登录github,访问个人页面
1. get形式访问 https://github.com/login
获取CSRFtoken
requests.get('https://github.com/login')
2. 向 https://github.com/session 发送POST
commit:Sign in
utf8:✓
authenticity_token:M8MJY6nIExIiqGfMWiz9b2A3hR7PZmo9Slh5g3mB7qZhWxFDo7rawaZT1sdT+/nvr6anQ3Hs+i/hwE0pE4rGMw==
login:root
password:sdfgsdfg
response = requests.post(
url= "https://github.com/session",
data={
commit:Sign in
utf8:✓
authenticity_token:M8MJY6nIExIiqGfMWiz9b2A3hR7PZmo9Slh5g3mB7qZhWxFDo7rawaZT1sdT+/nvr6anQ3Hs+i/hwE0pE4rGMw==
login:root
password:sdfgsdfg
}
)
response.text
response.cookies
3. 请求需要登录之后才能有权限查看的url
requests.get(
url='sdfasdfasdfasdfasdfasdf',
cookies={....}
)
"""
import requests
from bs4 import BeautifulSoup
# 第一步：获取csrf
r1 = requests.get(url='https://github.com/login')
b1 = BeautifulSoup(r1.text,'html.parser')
tag = b1.find(name='input',attrs={'name': 'authenticity_token'})
token = tag.get('value')
r1_cookie = r1.cookies.get_dict()
print('第一次',r1_cookie)
# 第二步：发送POST请求携带用户名密码,携带cookie，后台进行授权
# r2 = requests.post()
# r2 = requests.request('post',)
# print(token)
r2 = requests.post(
url='https://github.com/session',
data={
'commit': 'Sign in',
'utf8': '',
'authenticity_token': token,
'login': '你的账号',
'password': '你的密码'
},
cookies = r1_cookie
)
# 1. 根据
# r2获取状态码
# r2获取响应头【location】
# 2. 根据错误提示
r2_cookie = r2.cookies.get_dict()
r1_cookie.update(r2_cookie)
print('第二次',r2_cookie)
# 第三步：访问个人页面，携带cookie
r3 = requests.get(
url='https://github.com/settings/repositories',
cookies=r1_cookie
)
print(r3.text)
所以,需要登录页面才可查看的页面,需要附带cookies信息过去:
requests.get(
url='sdfasdfasdfasdfasdfasdf',
cookies={....}
)
请求头和请求体
有一篇文章写的挺好，适合入门：HTTP请求行、请求头、请求体详解
扩展
coockies，有请求头和响应体两部分组成
http请求，有请求头和请求体两部分组成
请求头和请求体有两个\r\n分割，请求头中每一个由一个\r\n分割。当然，这是转为text的显示，实际中这些是被隐藏掉的。HTTP使用\r\n来换行。
"GET /mike.html HTTP/1.1\r\n"
"Accept: image/gif, image/jpeg, image/pjpeg, application/x-ms-application, application/xaml+xml, application/x-ms-xbap, */*\r\n"
"Accept-Language: zh-Hans-CN,zh-Hans;q=0.8,en-US;q=0.5,en;q=0.3\r\n"
"User-Agent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729)\r\n"
"Accept-Encoding: gzip, deflate\r\n"
"Host: 192.168.48.98:8000\r\n"
"Connection: Keep-Alive\r\n"
"\r\n"
\r\n\r\n
请求body....
Content-Type
MediaType，即是Internet Media Type，互联网媒体类型；也叫做MIME类型，在Http协议消息头中，使用Content-Type来表示具体请求中的媒体类型信息。
类型格式：type/subtype(;parameter)? type 主类型，任意的字符串，如text，如果是*号代表所有； subtype 子类型，任意的字符串，如html，如果是*号代表所有； parameter 可选，一些参数，如Accept请求头的q参数， Content-Type的 charset参数。
例如： Content-Type: text/html;charset:utf-8;
常见的媒体格式类型如下：
text/html ： HTML格式
text/plain ：纯文本格式
text/xml ： XML格式
image/gif ：gif图片格式
image/jpeg ：jpg图片格式
image/png：png图片格式
#以application开头的媒体格式类型：
application/xhtml+xml ：XHTML格式
application/xml ： XML数据格式
application/atom+xml ：Atom XML聚合格式
application/json ： JSON数据格式
application/pdf ：pdf格式
application/msword ： Word文档格式
application/octet-stream ： 二进制流数据（如常见的文件下载）
application/x-www-form-urlencoded ： <form encType=””>中默认的encType，form表单数据被编码为key/value格式发送到服务器（表单默认的提交数据的格式）
另外一种常见的媒体格式是上传文件之时使用的：
multipart/form-data ： 需要在表单中进行文件上传时，就需要使用该格式
以上就是我们在日常的开发中，经常会用到的若干content-type的内容格式。
location重定向
如果http header中有跳转,会有location表示其重定向
requests模块
Python标准库中提供了：urllib、urllib2、httplib等模块以供Http请求，但毕竟已现老态，所有有了requests模块，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，使用Requests可以轻而易举的完成浏览器可有的任何操作。
get请求
# 1、无参数实例
import requests
ret = requests.get('https://github.com/timeline.json')
print ret.url
print ret.text
#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
import requests
#
# requests.get(
# url='http://www.baidu.com',
# params={'k1':123,'k3': 456},
# cookies={'c1':'123','c2':123},
# headers={
# 'Referer':'https://github.com/',
# 'User-Agent':"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36"
# }
# )
POST请求
# 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
#
# requests.post(
# data={'k1':'v1','k2':'v2'} #
# )
# 请求头
# Content-Type:application/x-www-form-urlencoded
# 请求体
# k1=v1&k2=v2
# Django
# def index(request):
#
# requests.body # k1=v1&k2=v2
# # 读取请求头中的Content-Type:application/x-www-form-urlencoded
# # request.POST # {....}
其他请求
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础上构建 requests.request(method, url, **kwargs)
参数列表
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]>
"""
使用展示
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
#页面打开后弹出登录页面,无法查看源文件,需要使用auth参数,真实情况比如路由器管理界面,zookeeper管理界面等等
def param_auth():
from requests.auth import HTTPBasicAuth, HTTPDigestAuth
ret = requests.get('https://api.github.com/user', auth=HTTPBasicAuth('usernamesss', 'passwdaxxxx'))
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)
#
# auth
# 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)
# # 请求头中 Authorization：加密（用户和密码）
#
# ret = requests.get('http://httpbin.org/digest-auth/auth/user/pass', auth=HTTPDigestAuth('user', 'pass'))
# print(ret.text)
#
# param_auth()
######################
def param_timeout():
#timeout定义了两个时间,连接时间,发送时间,本例连接/发送时间均为1秒超时
# ret = requests.get('http://google.com/', timeout=1)
# print(ret)
#连接时间5秒,发送时间1秒
# ret = requests.get('http://google.com/', timeout=(5, 1))
# print(ret)
pass
#如果你使用的是GET或OPTIONS，那么你可以通过 allow_redirects 参数禁用重定向处理
def param_allow_redirects():
ret = requests.get('http://127.0.0.1:8000/test/', allow_redirects=False)
print(ret.text)
#代理服务器
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
#如果下载文件很大,开启stream流,减小内存压力
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)
#设置session
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': "8615131255089",
'password': "xxxxxx",
'oneMonth': ""
}
)
i3 = session.post(
url="http://dig.chouti.com/link/vote?linksId=8589623",
)
print(i3.text)
最常用总结
response = requests.get(url='xx',cookies={...})
response.text
#将cookies序列化为字典类型的对象
response.cookies.get_dict()
response = requests.post(url='xx',cookies={...},data={})
response.text
response.cookies.get_dict()
BeautifulSoup
BeautifulSoup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。简化了pythoner编写正则的流程，省心省事儿。
安装:
pip3 install beautifulsoup4
看下用例:
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')
使用例子2:
from bs4 import BeautifulSoup
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
...
</body>
</html>
"""
soup = BeautifulSoup(html_doc, features="lxml")
features参数
被不同的TreeBuliders使用的解析器有以下三种：
- lxml
- html5lib
- html.parser
使用lxml/html5lib 需要安装额外的库.
当创建一个BeautifulSoup对象时，TreeBuliders类被用于创建HTML/XML树，默认的是使用HTML TreeBuliders对象，使用HTML解析器。如果我们想把输入当做XML做解析，我们必须明确的使用features参数在BeatufulSoup对象构造器中进行说明。指定features参数，我们能够选择最合适的TreeBuliders来满足我们的需求。
参数说明
name，标签名称
# tag = soup.find('a')
# name = tag.name # 获取
# print(name)
# tag.name = 'span' # 设置
# print(soup)
attr，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)
这里需要注意的是,如果使用attr设置属性,是重置所有的属性,并设置为指定的,如果标签有多个属性,使用attr设置后,会删除所有的属性并设置为指定属性.
children,所有子标签
只找第一层
# body = soup.find('body')
# v = body.children
descendants,子子孙孙标签
# body = soup.find('body')
# v = body.descendants
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)
decompose,递归的删除所有的标签
# body = soup.find('body')
# body.decompose()
# print(soup)
extract,递归的删除所有的标签，并获取删除的标签，类似列表里的pop
# body = soup.find('body')
# v = body.extract()
# print(soup)
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)
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)
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_all,获取匹配的所有标签,结果是个列表
# 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)
has_attr,检查标签是否具有该属性
# tag = soup.find('a')
# v = tag.has_attr('id')
# print(v)
get_text,获取标签内部文本内容
# tag = soup.find('a')
# v = tag.get_text('id')
# print(v)
#也可用text获取
#v = tag.text
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)
is_empty_element,是否是空标签(是否可以是空)或者自闭合标签
判断是否是如下自闭合标签：'br' , 'hr', 'input', 'img', 'meta','spacer', 'link', 'frame', 'base'
# tag = soup.find('br')
# v = tag.is_empty_element
# print(v)
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
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
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)
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)
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)
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_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)
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)
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)
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)
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)
from bs4 import BeautifulSoup
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
hello,world!
<a>百度<div>
<span>s1</span>
<div>asdf</div>
</div></a>
</body>
</html>
"""
soup = BeautifulSoup(html_doc, features="html.parser")
# body_obj = soup.find(name='body')
from bs4.element import Tag,NavigableString
# for item in body_obj.children:
# print('-->',item,type(item))
# div = soup.find(name='div')
# a = soup.find('a')
# div.wrap(a)
# print(soup)
a = soup.find('a')
a.unwrap()
print(soup)
自动登录实例
博客园
#!/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)
知乎
#!/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)
github
#!/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)
抽屉
#!/usr/bin/env python
# -*- coding:utf-8 -*-
import requests
# ############## 方式一 ##############
"""
# ## 1、首先登陆任何页面，获取cookie
i1 = requests.get(url="http://dig.chouti.com/help/service")
i1_cookies = i1.cookies.get_dict()
# ## 2、用户登陆，携带上一次的cookie，后台对cookie中的 gpsd 进行授权
i2 = requests.post(
url="http://dig.chouti.com/login",
data={
'phone': "8615131255089",
'password': "xxooxxoo",
'oneMonth': ""
},
cookies=i1_cookies
)
# ## 3、点赞（只需要携带已经被授权的gpsd即可）
gpsd = i1_cookies['gpsd']
i3 = requests.post(
url="http://dig.chouti.com/link/vote?linksId=8589523",
cookies={'gpsd': gpsd}
)
print(i3.text)
"""
# ############## 方式二 ##############
"""
import requests
session = requests.Session()
i1 = session.get(url="http://dig.chouti.com/help/service")
i2 = session.post(
url="http://dig.chouti.com/login",
data={
'phone': "8615131255089",
'password': "xxooxxoo",
'oneMonth': ""
}
)
i3 = session.post(
url="http://dig.chouti.com/link/vote?linksId=8589523"
)
print(i3.text)
"""
来源：https://www.cnblogs.com/ccorz/p/pa-chong-xiang-guan.html