爬虫库requests
一 介绍
#介绍:使用requests可以模拟浏览器的请求,比起之前用到的urllib,requests模块的api更加便捷(本质就是封装了urllib3) #注意:requests库发送请求将网页内容下载下来以后,并不会执行js代码,这需要我们自己分析目标站点然后发起新的request请求 #安装:pip3 install requests #各种请求方式:常用的就是requests.get()和requests.post() >>> import requests >>> r = requests.get('https://api.github.com/events') >>> r = requests.post('http://httpbin.org/post', data = {'key':'value'}) >>> r = requests.put('http://httpbin.org/put', data = {'key':'value'}) >>> r = requests.delete('http://httpbin.org/delete') >>> r = requests.head('http://httpbin.org/get') >>> r = requests.options('http://httpbin.org/get') #建议在正式学习requests前,先熟悉下HTTP协议 https://www.cnblogs.com/kermitjam/articles/9692568.html
二 基于GET请求
1、基本请求
import requests response=requests.get('http://dig.chouti.com/') print(response.text)
2、带参数的GET请求->params
import requests response=requests.get('https://s.taobao.com/search?q=手机') response=requests.get('https://s.taobao.com/search',params={"q":"美女"})
3、带参数的GET请求->headers
#通常我们在发送请求时都需要带上请求头,请求头是将自身伪装成浏览器的关键,常见的有用的请求头如下 Host Referer #大型网站通常都会根据该参数判断请求的来源 User-Agent #客户端 Cookie #Cookie信息虽然包含在请求头里,但requests模块有单独的参数来处理他,headers={}内就不要放它了
#添加headers(浏览器会识别请求头,不加可能会被拒绝访问,比如访问https://www.zhihu.com/explore) import requests response=requests.get('https://www.zhihu.com/explore') response.status_code #500 #自己定制headers headers={ 'User-Agent':'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.76 Mobile Safari/537.36', } respone=requests.get('https://www.zhihu.com/explore', headers=headers) print(respone.status_code) #200
4、带参数的GET请求->cookies
import uuid import requests url = 'http://httpbin.org/cookies' cookies = dict(sbid=str(uuid.uuid4())) res = requests.get(url, cookies=cookies) print(res.json())
三 基于POST请求
1、介绍
#GET请求 HTTP默认的请求方法就是GET * 没有请求体 * 数据必须在1K之内! * GET请求数据会暴露在浏览器的地址栏中 GET请求常用的操作: 1. 在浏览器的地址栏中直接给出URL,那么就一定是GET请求 2. 点击页面上的超链接也一定是GET请求 3. 提交表单时,表单默认使用GET请求,但可以设置为POST #POST请求 (1). 数据不会出现在地址栏中 (2). 数据的大小没有上限 (3). 有请求体 (4). 请求体中如果存在中文,会使用URL编码! #!!!requests.post()用法与requests.get()完全一致,特殊的是requests.post()有一个data参数,用来存放请求体数据
2、发送post请求,模拟浏览器的登录行为
#对于登录来说,应该输错用户名或密码然后分析抓包流程,用脑子想一想,输对了浏览器就跳转了,还分析个毛线,累死你也找不到包
''' 一 目标站点分析 浏览器输入https://github.com/login 然后输入错误的账号密码,抓包 发现登录行为是post提交到:https://github.com/session 而且请求头包含cookie 而且请求体包含: commit:Sign in utf8:✓ authenticity_token:lbI8IJCwGslZS8qJPnof5e7ZkCoSoMn6jmDTsL1r/m06NLyIbw7vCrpwrFAPzHMep3Tmf/TSJVoXWrvDZaVwxQ== login:maple password:123 二 流程分析 先GET:https://github.com/login拿到初始cookie与authenticity_token 返回POST:https://github.com/session, 带上初始cookie,带上请求体(authenticity_token,用户名,密码等) 最后拿到登录cookie ps:如果密码时密文形式,则可以先输错账号,输对密码,然后到浏览器中拿到加密后的密码,github的密码是明文 ''' import requests import re #第一次请求 r1=requests.get('https://github.com/login') r1_cookie=r1.cookies.get_dict() #拿到初始cookie(未被授权) authenticity_token=re.findall(r'name="authenticity_token".*?value="(.*?)"',r1.text)[0] #从页面中拿到CSRF TOKEN #第二次请求:带着初始cookie和TOKEN发送POST请求给登录页面,带上账号密码 data={ 'commit':'Sign in', 'utf8':'✓', 'authenticity_token':authenticity_token, 'login':'maple@qq.com', 'password':'123' } r2=requests.post('https://github.com/session', data=data, cookies=r1_cookie ) login_cookie=r2.cookies.get_dict() #第三次请求:以后的登录,拿着login_cookie就可以,比如访问一些个人配置 r3=requests.get('https://github.com/settings/emails', cookies=login_cookie) print('maple@qq.com' in r3.text) #True 自动登录github(自己处理cookie信息)
import requests import re session=requests.session() #第一次请求 r1=session.get('https://github.com/login') authenticity_token=re.findall(r'name="authenticity_token".*?value="(.*?)"',r1.text)[0] #从页面中拿到CSRF TOKEN #第二次请求 data={ 'commit':'Sign in', 'utf8':'✓', 'authenticity_token':authenticity_token, 'login':'maple@qq.com', 'password':'123' } r2=session.post('https://github.com/session', data=data, ) #第三次请求 r3=session.get('https://github.com/settings/emails') print('maple@qq.com' in r3.text) #True requests.session()自动帮我们保存cookie信息
3、补充
requests.post(url='xxxxxxxx', data={'xxx':'yyy'}) #没有指定请求头,#默认的请求头:application/x-www-form-urlencoed #如果我们自定义请求头是application/json,并且用data传值, 则服务端取不到值 requests.post(url='', data={'':1,}, headers={ 'content-type':'application/json' }) requests.post(url='', json={'':1,}, ) #默认的请求头:application/json
四 响应Response
1、response属性
import requests respone=requests.get('http://www.jianshu.com') # respone属性 #获取所有内容 print(respone.text) #获取二进制 print(respone.content) #获取状态码,如200,301等 print(respone.status_code) print(respone.headers) print(respone.cookies) #获取cookie print(respone.cookies.get_dict()) print(respone.cookies.items()) print(respone.url) print(respone.history) #获取编码 print(respone.encoding) #解决乱码 print(response.apparent_encoding)
2、编码问题
#编码问题 import requests response=requests.get('http://www.autohome.com/news') #方式一: # response.encoding='gbk' #汽车之家网站返回的页面内容为gb2312编码的,而requests的默认编码为ISO-8859-1,如果不设置成gbk则中文乱码 print(response.text) #方式二: #在不知道编码格式的前提下使用以下方式 response.encoding=response.apparent_encoding print(response.text)
3、获取二进制数据
import requests response=requests.get('https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1509868306530&di=712e4ef3ab258b36e9f4b48e85a81c9d&imgtype=0&src=http%3A%2F%2Fc.hiphotos.baidu.com%2Fimage%2Fpic%2Fitem%2F11385343fbf2b211e1fb58a1c08065380dd78e0c.jpg') with open('a.jpg','wb') as f: f.write(response.content)
4、解析json
#解析json import requests response=requests.get('http://httpbin.org/get') import json res1=json.loads(response.text) #太麻烦 res2=response.json() #直接获取json数据 print(res1 == res2) #True
五 高级用法
1、SSL Cert Verification
#证书验证(大部分网站都是https) import requests # 如果是ssl请求,首先检查证书是否合法,不合法则报错,程序终端 response = requests.get('https://www.xiaohuar.com') print(response.status_code) # 改进1:去掉报错,但是会报警告 import requests response = requests.get('https://www.xiaohuar.com', verify=False) # 不验证证书,报警告,返回200 print(response.status_code) # 改进2:去掉报错,并且去掉警报信息 import requests import urllib3 urllib3.disable_warnings() # 关闭警告 response = requests.get('https://www.xiaohuar.com', verify=False) print(response.status_code) # 改进3:加上证书 # 很多网站都是https,但是不用证书也可以访问,大多数情况都是可以携带也可以不携带证书 # 知乎\百度等都是可带可不带 # 有硬性要求的,则必须带,比如对于定向的用户,拿到证书后才有权限访问某个特定网站 import requests import urllib3 # urllib3.disable_warnings() # 关闭警告 response = requests.get( 'https://www.xiaohuar.com', # verify=False, cert=('/path/server.crt', '/path/key')) print(response.status_code)
2、使用代理
# 官网链接: http://docs.python-requests.org/en/master/user/advanced/#proxies # 代理设置:先发送请求给代理,然后由代理帮忙发送(封ip是常见的事情) import requests proxies={ # 带用户名密码的代理,@符号前是用户名与密码 'http':'http://tank:123@localhost:9527', 'http':'http://localhost:9527', 'https':'https://localhost:9527', } response=requests.get('https://www.12306.cn', proxies=proxies) print(response.status_code) # 支持socks代理,安装:pip install requests[socks] import requests proxies = { 'http': 'socks5://user:pass@host:port', 'https': 'socks5://user:pass@host:port' } respone=requests.get('https://www.12306.cn', proxies=proxies) print(respone.status_code)
from urllib.parse import urlencode import pymongo import requests from lxml.etree import XMLSyntaxError from requests.exceptions import ConnectionError from pyquery import PyQuery as pq # from config import * # # client = pymongo.MongoClient(MONGO_URI) # db = client[MONGO_DB] base_url = 'http://weixin.sogou.com/weixin?' headers = { 'Cookie': 'SUID=F6177C7B3220910A000000058E4D679; SUV=1491392122762346; ABTEST=1|1491392129|v1; SNUID=0DED8681FBFEB69230E6BF3DFB2F8D6B; ld=OZllllllll2Yi2balllllV06C77lllllWTZgdkllll9lllllxv7ll5@@@@@@@@@@; LSTMV=189%2C31; LCLKINT=1805; weixinIndexVisited=1; SUIR=0DED8681FBFEB69230E6BF3DFB2F8D6B; JSESSIONID=aaa-BcHIDk9xYdr4odFSv; PHPSESSID=afohijek3ju93ab6l0eqeph902; sct=21; IPLOC=CN; ppinf=5|1491580643|1492790243|dHJ1c3Q6MToxfGNsaWVudGlkOjQ6MjAxN3x1bmlxbmFtZToyNzolRTUlQjQlOTQlRTUlQkElODYlRTYlODklOER8Y3J0OjEwOjE0OTE1ODA2NDN8cmVmbmljazoyNzolRTUlQjQlOTQlRTUlQkElODYlRTYlODklOER8dXNlcmlkOjQ0Om85dDJsdUJfZWVYOGRqSjRKN0xhNlBta0RJODRAd2VpeGluLnNvaHUuY29tfA; pprdig=j7ojfJRegMrYrl96LmzUhNq-RujAWyuXT_H3xZba8nNtaj7NKA5d0ORq-yoqedkBg4USxLzmbUMnIVsCUjFciRnHDPJ6TyNrurEdWT_LvHsQIKkygfLJH-U2MJvhwtHuW09enCEzcDAA_GdjwX6_-_fqTJuv9w9Gsw4rF9xfGf4; sgid=; ppmdig=1491580643000000d6ae8b0ebe76bbd1844c993d1ff47cea', 'Host': 'weixin.sogou.com', 'Upgrade-Insecure-Requests': '1', 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36' } proxy = None def get_proxy(): try: response = requests.get('http://127.0.0.1:5555/random') if response.status_code == 200: return response.text return None except ConnectionError: return None def get_html(url, count=1): print('Crawling', url) print('Trying Count', count) global proxy if count >= 5: print('Tried Too Many Counts') return None try: if proxy: proxies = { 'http': 'http://' + proxy } response = requests.get(url, allow_redirects=False, headers=headers, proxies=proxies) else: response = requests.get(url, allow_redirects=False, headers=headers) if response.status_code == 200: return response.text if response.status_code == 302: # Need Proxy print('302') proxy = get_proxy() if proxy: print('Using Proxy', proxy) return get_html(url) else: print('Get Proxy Failed') return None except ConnectionError as e: print('Error Occurred', e.args) proxy = get_proxy() count += 1 return get_html(url, count) def get_index(keyword, page): data = { 'query': keyword, 'type': 2, 'page': page } queries = urlencode(data) url = base_url + queries html = get_html(url) return html def parse_index(html): doc = pq(html) items = doc('.news-box .news-list li .txt-box h3 a').items() for item in items: yield item.attr('href') def get_detail(url): try: response = requests.get(url) if response.status_code == 200: return response.text return None except ConnectionError: return None def parse_detail(html): try: doc = pq(html) title = doc('.rich_media_title').text() content = doc('.rich_media_content').text() date = doc('#post-date').text() nickname = doc('#js_profile_qrcode > div > strong').text() wechat = doc('#js_profile_qrcode > div > p:nth-child(3) > span').text() return { 'title': title, 'content': content, 'date': date, 'nickname': nickname, 'wechat': wechat } except XMLSyntaxError: return None # def save_to_mongo(data): # if db['articles'].update({'title': data['title']}, {'$set': data}, True): # print('Saved to Mongo', data['title']) # else: # print('Saved to Mongo Failed', data['title']) def main(): for page in range(1, 101): html = get_index('Python', page) if html: article_urls = parse_index(html) for article_url in article_urls: article_html = get_detail(article_url) if article_html: article_data = parse_detail(article_html) print(article_data) # if article_data: # save_to_mongo(article_data) if __name__ == '__main__': main() 使用代理爬取微信新闻: 参考
3、超时设置
#超时设置 #两种超时:float or tuple #timeout=0.1 #代表接收数据的超时时间 #timeout=(0.1,0.2)#0.1代表链接超时 0.2代表接收数据的超时时间 import requests respone=requests.get('https://www.baidu.com', timeout=0.0001)
4、 认证设置
# 官网链接:http://docs.python-requests.org/en/master/user/authentication/ # 认证设置:登陆网站是,弹出一个框,要求你输入用户名密码(与alter很类似),此时是无法获取html的 # ps: https://www.cnblogs.com/post/readauth?url=/kermitjam/articles/10147263.html # 但本质原理是拼接成请求头发送 # r.headers['Authorization'] = _basic_auth_str(self.username, self.password) # 一般的网站都不用默认的加密方式,都是自己写 # 那么我们就需要按照网站的加密方式,自己写一个类似于_basic_auth_str的方法 # 得到加密字符串后添加到请求头 # r.headers['Authorization'] =func('.....') # 看一看默认的加密方式吧,通常网站都不会用默认的加密设置 import requests from requests.auth import HTTPBasicAuth r=requests.get('xxx',auth=HTTPBasicAuth('user','password')) print(r.status_code) # HTTPBasicAuth可以简写为如下格式 import requests r=requests.get('xxx',auth=('user','password')) print(r.status_code)
5、异常处理
#异常处理 import requests from requests.exceptions import * #可以查看requests.exceptions获取异常类型 try: r=requests.get('http://www.baidu.com',timeout=0.00001) except ReadTimeout: print('===:') # except ConnectionError: #网络不通 # print('-----') # except Timeout: # print('aaaaa') except RequestException: print('Error')
6、上传文件
import requests files={'file':open('a.jpg','rb')} respone=requests.post('http://httpbin.org/post',files=files) print(respone.status_code)