python之路 -- 爬虫 -- 常用模块
1.requests
Requests 是用Python语言编写，基于 urllib，采用 Apache2 Licensed 开源协议的 HTTP 库。它比 urllib 更加方便，可以节约我们大量的工作，完全满足 HTTP 测试需求。
requests模块的参数
1.1 get #发送get请求
requests.get( )的参数有：url、params、headers、cookies
1 requests.get( 2 url=”http: // www.oldboyedu.com”, 3 params = {“nid”:1,”name”:”xx”} # 实际上传入的url为http://www.oldboyedu.com？Nid=1&name=xx #url中传入参数 4 headers = {...}, 5 cookies = {...} 6 )
1.2 post #发送post请求
requests.post( )的参数有：url、params , haders , data , cookies
post中的参数用法和get中的一样，就不一一赘述了。
1.3 proxies
proxies --代理
1 # 发送文件，定制文件名(上传文件) 2 # file_dict = { 3 # 'f1': ('test.txt', open('readme', 'rb')) 4 # } 5 # requests.request(method='POST', 6 # url='http://127.0.0.1:8000/test/', 7 # files=file_dict)
1.4 json
当请求中提交的不是From Data作为数据，而是payload.时使用，导入json模块json.dumps（data）
post发送json数据
1 import requests 2 import json 3 4 r = requests.post('https://api.github.com/some/endpoint', data=json.dumps({'some': 'data'})) 5 print(r.json())
1.5 auth
做基本的认证
1.6 timeout
#超时时间 timeout=（m,n） #表示 请求时间最多n秒；响应时间最多等待接收m秒
1.7 allow_redirects
是否支持重定向，默认为True
1.8 stream
下载大文件是使用，一点一点的下载
1 ret = requests.get('http://127.0.0.1:8000/test/', stream=True) 2 for i in r.iter_content(): 3 print(i) 4 from contextlib import closing 5 with closing(requests.get('http://httpbin.org/get', stream=True)) as r: 6 # 在此处理响应。 7 for i in r.iter_content(): 8 print(i)
1.9 cert: 证书
1.10 verify: 确认
2.BeautifulSoup
Beautiful Soup 是一个可以从 HTML 或 XML 文件中提取数据的 Python 库.它能够通过你喜欢的转换器实现惯用的文档导航,查找,修改文档的方式.Beautiful Soup 会帮你节省数小时甚至数天的工作时间.
2.1 bs4的安装
pip install BeautifulSoup4
2.2 解析
1 import requests 2 from bs4 import BeautifulSoup 3 4 ret = requests.get("http://www.baidu.com") 5 soup = BeautifulSoup(ret.text,'html.parser') 6 print(soup) #打印解析出来的html
2.3 find和find_all 方法
1 div = soup.find(name="div",attrs={"id":"content-list"}) 2 # 找到标签名为div，id属性为content-list的标签，返回此div标签中的所有内容 3 items = div.find_all(name="div",attrs={"class":"item"}) 4 #找到标签名为div，class属性为item的所有标签，返回所有此class属性的div标签
一大波练习这两个爬虫最常用模块的实例：
1.自动登录抽屉并批量点赞
1 import requests 2 from bs4 import BeautifulSoup 3 4 #获取每一页页面的URL 5 for page in range(5,6): 6 pageurl = "https://dig.chouti.com/all/hot/recent/%s"%page 7 8 header = { 9 "User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36" 10 } 11 #循环访问每一页，并获取cookies 12 response = requests.get( 13 url=pageurl, 14 headers = header 15 ) 16 cookie1_dict = response.cookies.get_dict() 17 # response.encoding = response.apparent_encoding 18 # print(response.text) 19 20 # 发送post请求，进行登录 21 data = { 22 "phone":"********", 23 "password":"*******", 24 "oneMonth":1 25 } 26 response1 = requests.post(url="https://dig.chouti.com/login", 27 data=data, 28 headers=header, 29 cookies = cookie1_dict 30 ) 31 32 #找到每页的各个新闻的ID 33 soup = BeautifulSoup(response.text,"html.parser") 34 div = soup.find(name="div",attrs={"id":"content-list"}) 35 # print(div) 36 items = div.find_all(name="div",attrs={"class":"item"}) 37 for item in items: 38 id=item.find(name="div",attrs = {"class":"part2"}).get("share-linkid") 39 40 #进行点赞操作 41 response2 = requests.post(url="https://dig.chouti.com/link/vote?linksId=%s"%id, 42 headers={ 43 "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36" 44 }, 45 cookies = cookie1_dict 46 47 ) 48 print(response2.text)
2.自动登录GitHub并获取个人信息
1 import requests 2 from bs4 import BeautifulSoup 3 4 res = requests.get(url="https://github.com/login") 5 soup1 = BeautifulSoup(res.text,"html.parser") 6 tag = soup1.find(name='input', attrs={'name': 'authenticity_token'}) 7 authenticity_token = tag.get('value') 8 cookie1 = res.cookies.get_dict() 9 10 header={ 11 "User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36" 12 } 13 14 res_login = requests.post(url="https://github.com/session", 15 headers = header, 16 data = { 17 "commit":"Sign in", 18 "utf8":"✓", 19 "authenticity_token":authenticity_token, 20 "login":"******", 21 "password":"**********" 22 }, 23 cookies = cookie1 24 ) 25 cookie2 = res_login.cookies.get_dict() 26 # print(res_login.text) 27 28 res_message = requests.get(url="https://github.com/Aberwang", 29 headers=header, 30 cookies = cookie2, 31 ) 32 # print(res_message.text) 33 soup2 = BeautifulSoup(res_message.text,"html.parser") 34 div = soup2.find(name="div",attrs={"id":"js-pjax-container"}) 35 h1 = div.find(name="h1",attrs={"class":"vcard-names"}) 36 span = h1.find(name="span",attrs={"class":"p-nickname vcard-username d-block"}) 37 username = span.get_text() 38 print("获取到的用户名为：",username) 39 a = div.find(name="a",attrs={"class":"u-photo d-block tooltipped tooltipped-s"}) 40 img = a.find(name="img",attrs={"class":"avatar width-full rounded-2"}) 41 src = img.get("src") 42 print("获取到的用户头像地址为：",src)
3.汽车之家新闻抓取
1 import requests 2 from bs4 import BeautifulSoup 3 4 res = requests.get("https://www.autohome.com.cn/news/") #获取网页HTML内容 5 res.encoding = "gbk" 6 7 soup = BeautifulSoup(res.text,"html.parser") 8 #解析所获得的html页面 9 li_list = soup.find(id = "auto-channel-lazyload-article").find_all(name = "li") 10 for li in li_list: 11 title = li.find("h3") 12 if not title: 13 continue 14 summary = li.find("p") 15 url = li.find("a").get("href") 16 img = li.find('img').get('src') 17 print(title.text,url,summary.text,img)
4.自动登录码云并获取个人信息
1 import requests 2 from bs4 import BeautifulSoup 3 4 #获取token 5 r1 = requests.get("https://gitee.com/login") 6 r1.encoding = "utf-8" 7 soup = BeautifulSoup(r1.text,"html.parser") 8 token = soup.find(name = "input",attrs = {"name":"authenticity_token"}).get("value") 9 10 #将用户名，密码，token发送到服务端，以POST请求方式 11 12 13 date = { 14 "utf8":"✓", 15 "authenticity_token":token, 16 "redirect_to_url":"", 17 "user[login]":"***账号****", 18 'user[password]':"***密码***.", 19 "captcha":"", 20 "user[remember_me]":"0", 21 "commit":"登录" 22 } 23 r2 = requests.post("https://gitee.com/login",date) 24 25 cookie_dict = r2.cookies.get_dict() 26 r3 = requests.get("https://gitee.com/aberwang/projects",cookie_dict) 27 print(r3.text)
