爬虫一
初识爬虫
1 #! /usr/bin/env python 2 # encoding: utf-8 3 4 from bs4 import BeautifulSoup 5 import requests 6 7 8 response = requests.get("http://www.autohome.com.cn/news/") 9 # response.text 10 response.encoding = response.apparent_encoding # 解决爬虫乱码 11 12 soup = BeautifulSoup(response.text, features="html.parser") # 生成Soup对象 13 soup_obj = soup.find(id="auto-channel-lazyload-article") # find查找第一个符合条件的对象 14 15 li_list = soup_obj.find_all("li") # find_all查找所有符合的对象，查找出来的值在列表中 16 # print(target) 17 for i in li_list: 18 a = i.find("a") 19 if a: 20 a_attrs = a.attrs.get("href") # attrs查找属性 21 print(a_attrs) 22 a_h = a.find("h3") 23 print(a_h) 24 img = a.find("img") 25 print(img)
requests
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。
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。
requests属性
1 response = requests.get('URL') 2 response.text # 获取文本内容 3 response.content # 获取文本内容，字节 4 response.encoding # 设置返回结果的编码 5 response.aparent_encoding # 获取网站原始的编码 6 response.status_code # 状态码 7 response.cookies.get_dict() # cookies
1 - 方法关系 2 requests.get(.....) 3 requests.post(.....) 4 requests.put(.....) 5 requests.delete(.....) 6 ... 7 8 requests.request('POST'...) 9 - 参数 10 request.request 11 - method: 提交方式 12 - url: 提交地址 13 - params: 在URL中传递的参数,GET 14 requests.request( 15 method='GET', 16 url= 'http://www.oldboyedu.com', 17 params = {'k1':'v1','k2':'v2'} 18 ) 19 # http://www.oldboyedu.com?k1=v1&k2=v2 20 - data: 在请求体里传递的数据 21 22 requests.request( 23 method='POST', 24 url= 'http://www.oldboyedu.com', 25 params = {'k1':'v1','k2':'v2'}, 26 data = {'use':'alex','pwd': '123','x':[11,2,3]} 27 ) 28 29 请求头: 30 content-type: application/url-form-encod..... 31 32 请求体: 33 use=alex&pwd=123 34 35 36 - json 在请求体里传递的数据 37 requests.request( 38 method='POST', 39 url= 'http://www.oldboyedu.com', 40 params = {'k1':'v1','k2':'v2'}, 41 json = {'use':'alex','pwd': '123'} 42 ) 43 请求头: 44 content-type: application/json 45 46 请求体: 47 "{'use':'alex','pwd': '123'}" 48 49 PS: 字典中嵌套字典时 50 51 - headers 请求头 52 53 requests.request( 54 method='POST', 55 url= 'http://www.oldboyedu.com', 56 params = {'k1':'v1','k2':'v2'}, 57 json = {'use':'alex','pwd': '123'}, 58 headers={ 59 'Referer': 'http://dig.chouti.com/', 60 'User-Agent': "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36" 61 } 62 ) 63 - cookies Cookies 64 65 66 67 - files 上传文件 68 69 - auth 基本认证(headers中加入加密的用户名和密码) 70 71 - timeout 请求和响应的超时时间 72 73 - allow_redirects 是否允许重定向 74 75 - proxies 代理 76 77 - verify 是否忽略证书 78 79 - cert 证书文件 80 81 - stream 流的方式迭代下载 82 83 - session: 用于保存客户端历史访问信息
示例
1.GET请求
1 # 1、无参数实例 2 3 import requests 4 5 ret = requests.get('https://github.com/timeline.json') 6 7 print ret.url 8 print ret.text 9 10 11 12 # 2、有参数实例 13 14 import requests 15 16 payload = {'key1': 'value1', 'key2': 'value2'} 17 ret = requests.get("http://httpbin.org/get", params=payload) 18 19 print ret.url 20 print ret.text
2.POST请求
1 # 1、基本POST实例 2 3 import requests 4 5 payload = {'key1': 'value1', 'key2': 'value2'} 6 ret = requests.post("http://httpbin.org/post", data=payload) 7 8 print ret.text 9 10 11 # 2、发送请求头和数据实例 12 13 import requests 14 import json 15 16 url = 'https://api.github.com/some/endpoint' 17 payload = {'some': 'data'} 18 headers = {'content-type': 'application/json'} 19 20 ret = requests.post(url, data=json.dumps(payload), headers=headers) 21 22 print ret.text 23 print ret.cookies
3.其他请求
1 requests.get(url, params=None, **kwargs) 2 requests.post(url, data=None, json=None, **kwargs) # post用于创建新数据 3 requests.put(url, data=None, **kwargs) # put用于更新已存在的数据 4 requests.head(url, **kwargs) 5 requests.delete(url, **kwargs) 6 requests.patch(url, data=None, **kwargs) # patch是put的补充，用于更新局部数据 7 requests.options(url, **kwargs)
options用于请求服务器，你可以使用哪些请求方法，比如你不知道百度能不能用post,通过options，就能获取到可以使用的请求方法 8 9 # 以上方法均是在此方法的基础上构建 10 requests.request(method, url, **kwargs)
1 def param_method_url(): 2 # requests.request(method='get', url='http://127.0.0.1:8000/test/') 3 # requests.request(method='post', url='http://127.0.0.1:8000/test/') 4 pass 5 6 7 def param_param(): 8 # - 可以是字典 9 # - 可以是字符串 10 # - 可以是字节（ascii编码以内） 11 12 # requests.request(method='get', 13 # url='http://127.0.0.1:8000/test/', 14 # params={'k1': 'v1', 'k2': '水电费'}) 15 16 # requests.request(method='get', 17 # url='http://127.0.0.1:8000/test/', 18 # params="k1=v1&k2=水电费&k3=v3&k3=vv3") 19 20 # requests.request(method='get', 21 # url='http://127.0.0.1:8000/test/', 22 # params=bytes("k1=v1&k2=k2&k3=v3&k3=vv3", encoding='utf8')) 23 24 # 错误 25 # requests.request(method='get', 26 # url='http://127.0.0.1:8000/test/', 27 # params=bytes("k1=v1&k2=水电费&k3=v3&k3=vv3", encoding='utf8')) 28 pass 29 30 31 def param_data(): 32 # 可以是字典 33 # 可以是字符串 34 # 可以是字节 35 # 可以是文件对象 36 37 # requests.request(method='POST', 38 # url='http://127.0.0.1:8000/test/', 39 # data={'k1': 'v1', 'k2': '水电费'}) 40 41 # requests.request(method='POST', 42 # url='http://127.0.0.1:8000/test/', 43 # data="k1=v1; k2=v2; k3=v3; k3=v4" 44 # ) 45 46 # requests.request(method='POST', 47 # url='http://127.0.0.1:8000/test/', 48 # data="k1=v1;k2=v2;k3=v3;k3=v4", 49 # headers={'Content-Type': 'application/x-www-form-urlencoded'} 50 # ) 51 52 # requests.request(method='POST', 53 # url='http://127.0.0.1:8000/test/', 54 # data=open('data_file.py', mode='r', encoding='utf-8'), # 文件内容是：k1=v1;k2=v2;k3=v3;k3=v4 55 # headers={'Content-Type': 'application/x-www-form-urlencoded'} 56 # ) 57 pass 58 59 60 def param_json(): 61 # 将json中对应的数据进行序列化成一个字符串，json.dumps(...) 62 # 然后发送到服务器端的body中，并且Content-Type是 {'Content-Type': 'application/json'} 63 requests.request(method='POST', 64 url='http://127.0.0.1:8000/test/', 65 json={'k1': 'v1', 'k2': '水电费'}) 66 67 68 def param_headers(): 69 # 发送请求头到服务器端 70 requests.request(method='POST', 71 url='http://127.0.0.1:8000/test/', 72 json={'k1': 'v1', 'k2': '水电费'}, 73 headers={'Content-Type': 'application/x-www-form-urlencoded'} 74 ) 75 76 77 def param_cookies(): 78 # 发送Cookie到服务器端 79 requests.request(method='POST', 80 url='http://127.0.0.1:8000/test/', 81 data={'k1': 'v1', 'k2': 'v2'}, 82 cookies={'cook1': 'value1'}, 83 ) 84 # 也可以使用CookieJar（字典形式就是在此基础上封装） 85 from http.cookiejar import CookieJar 86 from http.cookiejar import Cookie 87 88 obj = CookieJar() 89 obj.set_cookie(Cookie(version=0, name='c1', value='v1', port=None, domain='', path='/', secure=False, expires=None, 90 discard=True, comment=None, comment_url=None, rest={'HttpOnly': None}, rfc2109=False, 91 port_specified=False, domain_specified=False, domain_initial_dot=False, path_specified=False) 92 ) 93 requests.request(method='POST', 94 url='http://127.0.0.1:8000/test/', 95 data={'k1': 'v1', 'k2': 'v2'}, 96 cookies=obj) 97 98 99 def param_files(): 100 # 发送文件 101 # file_dict = { 102 # 'f1': open('readme', 'rb') 103 # } 104 # requests.request(method='POST', 105 # url='http://127.0.0.1:8000/test/', 106 # files=file_dict) 107 108 # 发送文件，定制文件名 109 # file_dict = { 110 # 'f1': ('test.txt', open('readme', 'rb')) 111 # } 112 # requests.request(method='POST', 113 # url='http://127.0.0.1:8000/test/', 114 # files=file_dict) 115 116 # 发送文件，定制文件名 117 # file_dict = { 118 # 'f1': ('test.txt', "hahsfaksfa9kasdjflaksdjf") 119 # } 120 # requests.request(method='POST', 121 # url='http://127.0.0.1:8000/test/', 122 # files=file_dict) 123 124 # 发送文件，定制文件名 125 # file_dict = { 126 # 'f1': ('test.txt', "hahsfaksfa9kasdjflaksdjf", 'application/text', {'k1': '0'}) 127 # } 128 # requests.request(method='POST', 129 # url='http://127.0.0.1:8000/test/', 130 # files=file_dict) 131 132 pass 133 134 135 def param_auth(): 136 from requests.auth import HTTPBasicAuth, HTTPDigestAuth 137 138 ret = requests.get('https://api.github.com/user', auth=HTTPBasicAuth('wupeiqi', 'sdfasdfasdf')) 139 print(ret.text) 140 141 # ret = requests.get('http://192.168.1.1', 142 # auth=HTTPBasicAuth('admin', 'admin')) 143 # ret.encoding = 'gbk' 144 # print(ret.text) 145 146 # ret = requests.get('http://httpbin.org/digest-auth/auth/user/pass', auth=HTTPDigestAuth('user', 'pass')) 147 # print(ret) 148 # 149 150 151 def param_timeout(): 152 # ret = requests.get('http://google.com/', timeout=1) 153 # print(ret) 154 155 # ret = requests.get('http://google.com/', timeout=(5, 1)) 156 # print(ret) 157 pass 158 159 160 def param_allow_redirects(): 161 ret = requests.get('http://127.0.0.1:8000/test/', allow_redirects=False) 162 print(ret.text) 163 164 165 def param_proxies(): 166 # proxies = { 167 # "http": "61.172.249.96:80", 168 # "https": "http://61.185.219.126:3128", 169 # } 170 171 # proxies = {'http://10.20.1.128': 'http://10.10.1.10:5323'} 172 173 # ret = requests.get("http://www.proxy360.cn/Proxy", proxies=proxies) 174 # print(ret.headers) 175 176 177 # from requests.auth import HTTPProxyAuth 178 # 179 # proxyDict = { 180 # 'http': '77.75.105.165', 181 # 'https': '77.75.105.165' 182 # } 183 # auth = HTTPProxyAuth('username', 'mypassword') 184 # 185 # r = requests.get("http://www.google.com", proxies=proxyDict, auth=auth) 186 # print(r.text) 187 188 pass 189 190 191 def param_stream(): 192 ret = requests.get('http://127.0.0.1:8000/test/', stream=True) 193 print(ret.content) 194 ret.close() 195 196 # from contextlib import closing 197 # with closing(requests.get('http://httpbin.org/get', stream=True)) as r: 198 # # 在此处理响应。 199 # for i in r.iter_content(): 200 # print(i) 201 202 203 def requests_session(): 204 import requests 205 206 session = requests.Session() 207 208 ### 1、首先登陆任何页面，获取cookie 209 210 i1 = session.get(url="http://dig.chouti.com/help/service") 211 212 ### 2、用户登陆，携带上一次的cookie，后台对cookie中的 gpsd 进行授权 213 i2 = session.post( 214 url="http://dig.chouti.com/login", 215 data={ 216 'phone': "8615131255089", 217 'password': "xxxxxx", 218 'oneMonth': "" 219 } 220 ) 221 222 i3 = session.post( 223 url="http://dig.chouti.com/link/vote?linksId=8589623", 224 ) 225 print(i3.text) 226 227 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。
1 from bs4 import BeautifulSoup 2 3 html_doc = """ 4 <html><head><title>The Dormouse's story</title></head> 5 <body> 6 asdf 7 <div class="title"> 8 <b>The Dormouse's story总共</b> 9 <h1>f</h1> 10 </div> 11 <div class="story">Once upon a time there were three little sisters; and their names were 12 <a class="sister0" id="link1">Els<span>f</span>ie</a>, 13 <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and 14 <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>; 15 and they lived at the bottom of a well.</div> 16 ad<br/>sf 17 <p class="story">...</p> 18 </body> 19 </html> 20 """ 21 22 soup = BeautifulSoup(html_doc, features="lxml") 23 # 找到第一个a标签 24 tag1 = soup.find(name='a') 25 # 找到所有的a标签 26 tag2 = soup.find_all(name='a') 27 # 找到id＝link2的标签 28 tag3 = soup.select('#link2')
安装：
1 pip3 install beautifulsoup4
使用示例：
1 from bs4 import BeautifulSoup 2 3 html_doc = """ 4 <html><head><title>The Dormouse's story</title></head> 5 <body> 6 ... 7 </body> 8 </html> 9 """ 10 11 soup = BeautifulSoup(html_doc, features="lxml")
1. name，标签名称
1 # tag = soup.find('a') 2 # name = tag.name # 获取 3 # print(name) 4 # tag.name = 'span' # 设置 5 # print(soup)
2. attr，标签属性
1 # tag = soup.find('a') 2 # attrs = tag.attrs # 获取 3 # print(attrs) 4 # tag.attrs = {'ik':123} # 设置 5 # tag.attrs['id'] = 'iiiii' # 设置 6 # print(soup)
3. children,所有子标签
1 # body = soup.find('body') 2 # v = body.children
4. children,所有子子孙孙标签
1 # body = soup.find('body') 2 # v = body.descendants
5. clear,将标签的所有子标签全部清空（保留标签名）
1 # tag = soup.find('body') 2 # tag.clear() 3 # print(soup)
6. decompose,递归的删除所有的标签
1 # body = soup.find('body') 2 # body.decompose() 3 # print(soup)
7. extract,递归的删除所有的标签，并获取删除的标签
1 # body = soup.find('body') 2 # v = body.extract() 3 # print(soup)
8. decode,转换为字符串（含当前标签）；decode_contents（不含当前标签）
1 # body = soup.find('body') 2 # v = body.decode() 3 # v = body.decode_contents() 4 # print(v)
9. encode,转换为字节（含当前标签）；encode_contents（不含当前标签）
1 # body = soup.find('body') 2 # v = body.encode() 3 # v = body.encode_contents() 4 # print(v)
10. find,获取匹配的第一个标签
1 # tag = soup.find('a') 2 # print(tag) 3 # tag = soup.find(name='a', attrs={'class': 'sister'}, recursive=True, text='Lacie') 4 # tag = soup.find(name='a', class_='sister', recursive=True, text='Lacie') 5 # print(tag)
11. find_all,获取匹配的所有标签
1 # tags = soup.find_all('a') 2 # print(tags) 3 4 # tags = soup.find_all('a',limit=1) 5 # print(tags) 6 7 # tags = soup.find_all(name='a', attrs={'class': 'sister'}, recursive=True, text='Lacie') 8 # # tags = soup.find(name='a', class_='sister', recursive=True, text='Lacie') 9 # print(tags) 10 11 12 # ####### 列表 ####### 13 # v = soup.find_all(name=['a','div']) 14 # print(v) 15 16 # v = soup.find_all(class_=['sister0', 'sister']) 17 # print(v) 18 19 # v = soup.find_all(text=['Tillie']) 20 # print(v, type(v[0])) 21 22 23 # v = soup.find_all(id=['link1','link2']) 24 # print(v) 25 26 # v = soup.find_all(href=['link1','link2']) 27 # print(v) 28 29 # ####### 正则 ####### 30 import re 31 # rep = re.compile('p') 32 # rep = re.compile('^p') 33 # v = soup.find_all(name=rep) 34 # print(v) 35 36 # rep = re.compile('sister.*') 37 # v = soup.find_all(class_=rep) 38 # print(v) 39 40 # rep = re.compile('http://www.oldboy.com/static/.*') 41 # v = soup.find_all(href=rep) 42 # print(v) 43 44 # ####### 方法筛选 ####### 45 # def func(tag): 46 # return tag.has_attr('class') and tag.has_attr('id') 47 # v = soup.find_all(name=func) 48 # print(v) 49 50 51 # ## get,获取标签属性 52 # tag = soup.find('a') 53 # v = tag.get('id') 54 # print(v)
12. has_attr,检查标签是否具有该属性
1 # tag = soup.find('a') 2 # v = tag.has_attr('id') 3 # print(v)
13. get_text,获取标签内部文本内容
1 # tag = soup.find('a') 2 # v = tag.get_text('id') 3 # print(v)
14. index,检查标签在某标签中的索引位置
1 # tag = soup.find('body') 2 # v = tag.index(tag.find('div')) 3 # print(v) 4 5 # tag = soup.find('body') 6 # for i,v in enumerate(tag): 7 # 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'
1 # tag = soup.find('br') 2 # v = tag.is_empty_element 3 # print(v)
16. 当前的关联标签
1 # soup.next 2 # soup.next_element 3 # soup.next_elements 4 # soup.next_sibling 5 # soup.next_siblings 6 7 # 8 # tag.previous 9 # tag.previous_element 10 # tag.previous_elements 11 # tag.previous_sibling 12 # tag.previous_siblings 13 14 # 15 # tag.parent 16 # tag.parents
17. 查找某标签的关联标签
1 # tag.find_next(...) 2 # tag.find_all_next(...) 3 # tag.find_next_sibling(...) 4 # tag.find_next_siblings(...) 5 6 # tag.find_previous(...) 7 # tag.find_all_previous(...) 8 # tag.find_previous_sibling(...) 9 # tag.find_previous_siblings(...) 10 11 # tag.find_parent(...) 12 # tag.find_parents(...) 13 14 # 参数同find_all
