时间戳

首页 > 技术文章 > 爬虫

爬虫

glf1160 2018-07-03 15:59 原文

　　网络爬虫（又被称为网页蜘蛛，网络机器人，在FOAF社区中间，更经常的称为网页追逐者），是一种按照一定的规则，自动地抓取万维网信息的程序或者脚本。另外一些不常使用的名字还有蚂蚁、自动索引、模拟程序或者蠕虫。

Requests(官方文档：https://2.python-requests.org//zh_CN/latest/user/quickstart.html)

　　Python标准库中提供了：urllib、urllib2、httplib等模块以供Http请求，但是，它的 API 太渣了。它是为另一个时代、另一个互联网所创建的。它需要巨量的工作，甚至包括各种方法覆盖，来完成最简单的任务

import urllib2
import json
import cookielib


def urllib2_request(url, method="GET", cookie="", headers={}, data=None):
    """
    :param url: 要请求的url
    :param cookie: 请求方式，GET、POST、DELETE、PUT..
    :param cookie: 要传入的cookie，cookie= 'k1=v1;k1=v2'
    :param headers: 发送数据时携带的请求头，headers = {'ContentType':'application/json; charset=UTF-8'}
    :param data: 要发送的数据GET方式需要传入参数，data={'d1': 'v1'}
    :return: 返回元祖，响应的字符串内容 和 cookiejar对象
    对于cookiejar对象，可以使用for循环访问：
        for item in cookiejar:
            print item.name,item.value
    """
    if data:
        data = json.dumps(data)

    cookie_jar = cookielib.CookieJar()
    handler = urllib2.HTTPCookieProcessor(cookie_jar)
    opener = urllib2.build_opener(handler)
    opener.addheaders.append(['Cookie', 'k1=v1;k1=v2'])
    request = urllib2.Request(url=url, data=data, headers=headers)
    request.get_method = lambda: method

    response = opener.open(request)
    origin = response.read()

    return origin, cookie_jar


# GET
result = urllib2_request('http://127.0.0.1:8001/index/', method="GET")

# POST
result = urllib2_request('http://127.0.0.1:8001/index/',  method="POST", data= {'k1': 'v1'})

# PUT
result = urllib2_request('http://127.0.0.1:8001/index/',  method="PUT", data= {'k1': 'v1'})

封装urllib请求
View Code

　　Requests 是使用 Apache2 Licensed 许可证的 基于Python开发的HTTP 库，其在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，变得美好了许多，使用Requests可以轻而易举的完成浏览器可有的任何操作。

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)
# 获取cookie
res=requests.post(url)
cookie=res.cookies.get_dict() # 得到字典形式

 

参数：

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


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:
    # # 在此处理响应。
    # for i in r.iter_content():
    # print(i)


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)

参数示例
参数示例

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。

安装

 

pip3 install beautifulsoup4

 

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')
例子

1.name，标签名称

# tag = soup.find('a')
# name = tag.name # 获取
# print(name)
# tag.name = 'span' # 设置
# print(soup)
View Code

2.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)
View Code

3.children

　　(1)所有子标签

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

　　(2)所有子子孙孙标签

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

4.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)
View Code

5. decompose,递归的删除所有的标签

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

6. extract,递归的删除所有的标签，并获取删除的标签

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

7. 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)
View Code

8. 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)
View Code

9. 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)
View Code

10. find_all,获取匹配的所有标签

# 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)
View Code

11. has_attr,检查标签是否具有该属性

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

12. get_text,获取标签内部文本内容

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

13. 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)
View Code

14. 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)
View Code

15. 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
View Code

16. 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
View Code

17. 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)
View Code

18. 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)
View Code

19.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)
View Code

20.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)
View Code

21. 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)
View Code

22. 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)
View Code

23. 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)
View Code

24. 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)
View Code

25. 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)
View Code

简单的例子：

# 访问首页
import requests
from bs4 import BeautifulSoup

rs=requests.get(
    url="https://dig.chouti.com/",
    headers={"user-agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3423.2 Safari/537.36"}
)

# 登录
r2=requests.post(
    url="https://dig.chouti.com/login",
    headers={"user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3423.2 Safari/537.36"},
    data={
        "phone": "86+已注册电话号码",
        "password": "密码",
        "oneMonth": "1"
    },
cookies=rs.cookies.get_dict()

)
# print(r2.text)

#点赞
r3=requests.post(
    url="https://dig.chouti.com/link/vote?linksId=20438991",
    headers={"user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3423.2 Safari/537.36"},
    cookies=rs.cookies.get_dict()

)
print(r3.text)
抽屉网点赞

 beautifulsoup文档：http://beautifulsoup.readthedocs.io/zh_CN/v4.4.0/

 requests文档：https://2.python-requests.org//zh_CN/latest/user/quickstart.html

推荐阅读