爬虫：编写程序向网站发起请求，获取资源后分析并提取有用数据
requests
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
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) 或
ret = requests.post(url, json=payload, headers=headers)
print ret.text
print ret.cookies
其它请求
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
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_proxies(): #代理，如果封了ip就可以用代理 # 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_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_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)
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，之后则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
使用：
from bs4 import BeautifulSoup
bs4的用处：
-解析爬虫数据
-解析XHML数据
-用户提交数据，进行格式校验（KindEditor、UEditor）
1 soup = BeautifulSoup(html, "html.parser") 2 # 找到第一个a标签 3 tag1 = soup.find(name='a') 4 # 找到所有的a标签 5 tag2 = soup.find_all(name='a') 6 # 找到id＝link2的标签 7 tag3 = soup.select(attes={id='link2')
实例
import requests from bs4 import BeautifulSoup # 1、下载页面 ret=requests.get( url="https://www.autohome.com.cn/news/", ) # 字节内容 # print(ret.content) # 该网页的字节编码 # print(ret.apparent_encoding) ret.encoding=ret.apparent_encoding # 将byte转化为字符串格式 # print(ret.text) # 2、解析 # 获取指定内容 soup=BeautifulSoup(ret.text,"html.parser") #解析器 div=soup.find(name="div",id="auto-channel-lazyload-article") li_list=div.find_all(name="li") # print(li_list) for li in li_list: h3=li.find(name="h3") if not h3: continue a=li.find(name="a") href=(a.get("href")).strip("//") p=li.find(name="p") img=li.find(name="img") src=img.get("src") file_name=src.split("__")[1] # 获取图片 img_list=requests.get(url="https:%s"%src) print(img_list) # 写入文件 with open("img/%s"%file_name,"wb") as f: f.write(img_list.content) # print(h3.text) # print(href) # print(p.text)
import requests from bs4 import BeautifulSoup # 获取未授权的cookies ret1=requests.get( url="https://dig.chouti.com/", headers={ "User-Agent":'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36' } ) ret1_cookie=ret1.cookies.get_dict() # 登录 ret=requests.post( url='https://dig.chouti.com/login', data={ "phone":'xx', "password":"xx", "oneMonth":1 }, headers={ "User-Agent":'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36' }, cookies=ret1_cookie ) # 获取每页id for id in range(1,2): ret2=requests.get( url="https://dig.chouti.com/all/hot/recent/%s"%id, headers={ "User-Agent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36' }, cookies=ret1_cookie ) # print(ret2.text) soup=BeautifulSoup(ret2.text,"html.parser") div=soup.find(name="div",attrs={"class":"content-list","id":"content-list"}) items=div.find_all(name="div",attrs={"class":"item"}) for i in items: par2=i.find(name="div",attrs={"class":"part2"}) nid=par2.get("share-linkid") # 点赞 ret3=requests.post( url="https://dig.chouti.com/link/vote?linksId=%s"%nid, headers={ "User-Agent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36' }, cookies=ret1_cookie ) print(ret3.text)
模拟微信登录并获取信息
1、显示二维码
url+时间戳*1000，并保存xuuid（伪uuid）
长轮询：浏览器向微信服务器发送一个请求，服务器hold次连接（有一点时间限制），在次期间如果用户扫码则立即响应
轮询：浏览器短时间内，一直向服务器发送请求，
2、扫码
返回201和img，
3、确认登录
返回200和url ，在此url+“xxx”，再次发送请求，获取登录用户凭证相关的数据（XHML）， 将凭证数据和cookies保存
4、用户信息初始化
发post请求，发送用户凭证信息 json数据
5、获取 头像
- 图片防盗链
- Referer
- cookie
5、获取联系人信息
发请求带上cookies
示例：