目录
Requests模块简介
#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/liuqingzheng/p/10191056.html
基于GET请求
基本请求
import requests
response=requests.get('http://dig.chouti.com/')
print(response.text)
带参数的GET请求->params
import requests
response=requests.get('https://www.baidu.com/s?wd=python&pn=1',
headers={
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.75 Safari/537.36',
})
print(response.text)
# response.encoding=response.apparent_encoding
with open('ptyhon.html','wb') as f:
f.write(response.content)
#如果查询关键词是中文或者有其他特殊符号，则不得不进行url编码
from urllib.parse import urlencode,unquote # url的编码和解码
wd='美女'
encode_res=urlencode({'k':wd},encoding='utf-8')
keyword=encode_res.split('=')[1]
print(keyword)
# 然后拼接成url
url='https://www.baidu.com/s?wd=%s&pn=1' %keyword
response=requests.get(url,
headers={
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.75 Safari/537.36',
})
with open('girl.html','wb') as f:
f.write(response.content)
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
带参数的GET请求->cookies
import requests
# 方式一
Cookies={ 'user_session':'rzNme4L6LTH7QSresq8w0BVYhTNt5GS-asNnkOe7_FZ2CjB6',
}
response=requests.get('https://github.com/settings/emails',
cookies=Cookies) #github对请求头没有什么限制，我们无需定制user-agent，对于其他网站可能还需要定制
print('306334678@qq.com' in response.text) #True
# 方式二 cookies是一个字典或者CookieJar对象
header = {
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36',
'cookie':'key=asdfasdfasdfsdfsaasdf;key2=asdfasdf;key3=asdfasdf'
}
res=requests.get('https://github.com/settings/emails', headers=header)
基于POST请求
#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
发送post请求,模拟浏览器的登录
'''
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:egonlin
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':'317828332@qq.com',
'password':'alex3714'
}
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('317828332@qq.com' in r3.text) #True
自动登录gitbub（自己处理cookies））
# 使用session自动获取cookie
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':'317828332@qq.com',
'password':'alex3714'
}
r2=session.post('https://github.com/session',
data=data,
)
#第三次请求
r3=session.get('https://github.com/settings/emails')
print('317828332@qq.com' in r3.text) #True
requests.session()自动帮我们保存cookie信息
解析json
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
import json
respone=requests.post('http://127.0.0.1:8000/index/',data={'name':'lqz'})
print(type(respone.text)) # 响应的文本
print(json.loads(respone.text))
print(respone.json()) # 相当于上面那句话
响应Response
response属性
import requests
respone=requests.get('http://www.jianshu.com')
print(respone.text) # 响应的文本
print(respone.content) # 响应体的二进制
print(respone.status_code) # 响应状态码
print(respone.headers) # 响应头
print(respone.cookies) # cookie
print(respone.cookies.get_dict()) # 把cookie转成字典
print(respone.cookies.items()) # key和value
print(respone.url) # 请求的url
print(respone.history) #[]放重定向之前的地址
print(respone.encoding) # 响应的编码方式
respone.iter_content() # 图片，视频，大文件，一点一点循环取出来
#关闭：response.close()
from contextlib import closing
with closing(requests.get('xxx',stream=True)) as response:
for line in response.iter_content():
pass
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
# 方式二
response.encoding=response.apparent_encoding
print(response.text)
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)
# 二进制流
#stream参数:一点一点的取,比如下载视频时,如果视频100G,用response.content然后一下子写到文件中是不合理的
import requests
response=requests.get('https://gss3.baidu.com/6LZ0ej3k1Qd3ote6lo7D0j9wehsv/tieba-smallvideo-transcode/1767502_56ec685f9c7ec542eeaf6eac93a65dc7_6fe25cd1347c_3.mp4',
stream=True)
with open('b.mp4','wb') as f:
for line in response.iter_content():
f.write(line)
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
Redirection and History
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':'317828332@qq.com',
'password':'alex3714'
}
#测试一：没有指定allow_redirects=False,则响应头中出现Location就跳转到新页面，r2代表新页面的response
r2=requests.post('https://github.com/session',
data=data,
cookies=r1_cookie
)
print(r2.status_code) #200
print(r2.url) #看到的是跳转后的页面
print(r2.history) #看到的是跳转前的response
print(r2.history[0].text) #看到的是跳转前的response.text
#测试二：指定allow_redirects=False,则响应头中即便出现Location也不会跳转到新页面，r2代表的仍然是老页面的response
r2=requests.post('https://github.com/session',
data=data,
cookies=r1_cookie,
allow_redirects=False
)
print(r2.status_code) #302
print(r2.url) #看到的是跳转前的页面https://github.com/session
print(r2.history) #[]
利用github登录后跳转到主页面的例子来验证
高级用法
SSL Cert Verification
#证书验证(大部分网站都是https)
import requests
respone=requests.get('https://www.12306.cn') #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
#改进1:去掉报错,但是会报警告
import requests
respone=requests.get('https://www.12306.cn',verify=False) #不验证证书,报警告,返回200
print(respone.status_code)
#改进2:去掉报错,并且去掉警报信息
import requests
from requests.packages import urllib3
urllib3.disable_warnings() #关闭警告
respone=requests.get('https://www.12306.cn',verify=False)
print(respone.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
respone=requests.get('https://www.12306.cn',
cert=('/path/server.crt',
'/path/key'))
print(respone.status_code)
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={
'http':'http://egon:123@xxxxxxxx:9743',#带用户名密码的代理,@符号前是用户名与密码
'http':'27.46.20.226:8888',
'https':'https://xxxxxxx:9743',
}
respone=requests.get('https://www.12306.cn', proxies=proxies)
print(respone.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)
# 高匿和透明代理？如果使用高匿代理，后端无论如何拿不到你的ip，使用透明，后端能够拿到你的ip
# 后端如何拿到透明代理的ip,后端：X-Forwarded-For
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)
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
# 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)
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')
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)
单线程下载梨视频
import requests
import re
import time
def get_page(url):
try:
response=requests.get(url)
if response.status_code==200:
return response.text
except Exception as e:
print(e)
def get_detail(index_page):
urls=re.findall('class="categoryem".*?href="(.*?)"',index_page,re.S)
# print(urls)
for url in urls:
yield 'https://www.pearvideo.com/'+url
def pase_detail(detail_page):
# print(detail_page)
down_url=re.findall('srcUrl="(.*?)"',detail_page,re.S)[0]
print(down_url)
return down_url
def get_movie(url):
response=requests.get(url)
with open('movie/%s.mp4'%str(time.time()),'wb') as f:
f.write(response.content)
print('下载成功')
if __name__ == '__main__':
index_page=get_page('https://www.pearvideo.com/category_loading.jsp?reqType=5&categoryId=8&start=24')
urls=get_detail(index_page)
for url in urls:
print(url)
detail_page=get_page(url)
mp4_url=pase_detail(detail_page)
get_movie(mp4_url)
线程池下载梨视频
import requests
import re
import time
from concurrent.futures import ThreadPoolExecutor
pool=ThreadPoolExecutor(50)
def get_page(url):
try:
response=requests.get(url)
if response.status_code==200:
return response.text
except Exception as e:
print(e)
def pase_index(index_page):
index_page=index_page.result()
urls=re.findall('class="categoryem".*?href="(.*?)"',index_page,re.S)
# print(urls)
for url in urls:
next_url= 'https://www.pearvideo.com/'+url
pool.submit(get_page, next_url).add_done_callback(pase_detail)
def pase_detail(detail_page):
detail_page=detail_page.result()
# print(detail_page)
down_url=re.findall('srcUrl="(.*?)"',detail_page,re.S)[0]
pool.submit(get_movie, down_url)
def get_movie(url):
print(url)
response=requests.get(url)
with open('movie/%s.mp4'%str(time.time()),'wb') as f:
f.write(response.content)
print('下载成功')
if __name__ == '__main__':
for i in range(5):
url='https://www.pearvideo.com/category_loading.jsp?reqType=5&categoryId=8&start=%s'%((i+1)*12)
pool.submit(get_page, url).add_done_callback(pase_index)
获取汽车之家新闻并保存图片
import requests
from bs4 import BeautifulSoup
import os
for i in range(1, 10):
ret = requests.get(url='https://www.autohome.com.cn/news/%s/#liststart' % (i,))
ret.encoding = ret.apparent_encoding
soup = BeautifulSoup(ret.text, 'lxml')
div = soup.find(name='div', attrs={'id': 'auto-channel-lazyload-article'})
li_list = div.find_all(name='li')
for li in li_list:
h3 = li.find(name='h3')
if not h3:
continue
p_text = li.find(name='p').text
href = li.find(name='a').get('href')
img = li.find(name='img').get('src')
print('''
新闻标题：%s
新闻简介：%s
新闻地址：%s
新闻图片：%s
''' % (h3.text, p_text, 'https:' + href, 'https:' + img))
ret_photo = requests.get(url='https:' + img)
photo_name = img.rsplit('__', 1)[-1]
if not os.path.exists('download'):
os.mkdir('download')
with open('download/' + photo_name, 'wb') as f:
f.write(ret_photo.content)
自动登录抽屉自动点赞,评论
import requests
from bs4 import BeautifulSoup
import time
# 打开抽屉首页
ret = requests.get(url='https://dig.chouti.com/',
headers={
'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36',
# 'accept-language': 'zh-CN,zh;q=0.9'
}
)
# print(ret.text)
coo = ret.cookies.get_dict()
print(coo)
# 8613121758648
# woshiniba
# 登录到抽屉
ret_login = requests.post(url='https://dig.chouti.com/login',
headers={
'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'
},
data={
'phone': '8618953675221',
'password': 'lqz123',
'oneMonth': '1'
},
cookies=coo
)
print(ret_login.text)
# print(ret_login.cookies.get_dict())
# https://dig.chouti.com/link/vote?linksId=21055766
# ret_post = requests.post(url='https://dig.chouti.com/link/vote?linksId=21055766',
# headers={
# 'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'
# },
# cookies=coo
# )
# print(ret_post.text)
for i in range(2,3):
ret_index = requests.get(url='https://dig.chouti.com/all/hot/recent/%s'%i,
headers={
'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36',
}
)
soup = BeautifulSoup(ret_index.text, 'html.parser')
div = soup.find(name='div', attrs={'id': 'content-list'})
# print(div)
item_list = div.find_all(name='div', attrs={'class': 'item'})
print(item_list)
for item in item_list:
part2_div = item.find(name='div', attrs={'class': 'part2'})
nid = part2_div.get('share-linkid')
print(nid)
time.sleep(0.5)
ret_post = requests.post(url='https://dig.chouti.com/link/vote?linksId=%s' % nid,
headers={
'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'
},
cookies=coo
)
print(ret_post.text)
# 给文章评论
# ret_post = requests.post(url='https://dig.chouti.com/comments/create',
# headers={
# 'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'
# },
# cookies=coo,
# data={
# 'jid': 'cdu_53207078460',
# 'linkId': '21061426',
# 'isAssent': '',
# 'content': '写的真好',
# 'sortType':'score'
#
# }
# )
爬取bilibili视频
'''
通过该程序下载的视频和音频是分成连个文件的，没有合成，
视频为：视频名_video.mp4
音频为：视频名_audio.mp4
修改url的值，换成自己想下载的页面节课
'''
# 导入requests模块，模拟发送请求
import requests
# 导入json
import json
# 导入re
import re
# 定义请求头
headers = {
'Accept': '*/*',
'Accept-Language': 'en-US,en;q=0.5',
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36'
}
# 正则表达式，根据条件匹配出值
def my_match(text, pattern):
match = re.search(pattern, text)
print(match.group(1))
print()
return json.loads(match.group(1))
def download_video(old_video_url, video_url, audio_url, video_name):
headers.update({"Referer": old_video_url})
print("开始下载视频：%s" % video_name)
video_content = requests.get(video_url, headers=headers)
print('%s视频大小：' % video_name, video_content.headers['content-length'])
audio_content = requests.get(audio_url, headers=headers)
print('%s音频大小：' % video_name, audio_content.headers['content-length'])
# 下载视频开始
received_video = 0
with open('%s_video.mp4' % video_name, 'ab') as output:
while int(video_content.headers['content-length']) > received_video:
headers['Range'] = 'bytes=' + str(received_video) + '-'
response = requests.get(video_url, headers=headers)
output.write(response.content)
received_video += len(response.content)
# 下载视频结束
# 下载音频开始
audio_content = requests.get(audio_url, headers=headers)
received_audio = 0
with open('%s_audio.mp4' % video_name, 'ab') as output:
while int(audio_content.headers['content-length']) > received_audio:
# 视频分片下载
headers['Range'] = 'bytes=' + str(received_audio) + '-'
response = requests.get(audio_url, headers=headers)
output.write(response.content)
received_audio += len(response.content)
# 下载音频结束
return video_name
if __name__ == '__main__':
# 换成你要爬取的视频地址
url = 'https://www.bilibili.com/video/av76609390'
# 发送请求，拿回数据
res = requests.get(url, headers=headers)
# 视频详情json
playinfo = my_match(res.text, '__playinfo__=(.*?)</script><script>')
# 视频内容json
initial_state = my_match(res.text, r'__INITIAL_STATE__=(.*?);(function()')
# 视频分多种格式，直接取分辨率最高的视频 1080p
video_url = playinfo['data']['dash']['video'][0]['baseUrl']
# 取出音频地址
audio_url = playinfo['data']['dash']['audio'][0]['baseUrl']
video_name = initial_state['videoData']['title']
print('视频名字为：video_name')
print('视频地址为：', video_url)
print('音频地址为：', audio_url)
download_video(url, video_url, audio_url, video_name)
## you-get版
import requests
from you_get.common import any_download
from concurrent.futures import ThreadPoolExecutor
import ssl
pool = ThreadPoolExecutor(10)
# 生成证书上下文(unverified 就是不验证https证书)
ssl._create_default_https_context = ssl._create_unverified_context
res_json=requests.get('https://api.bilibili.com/x/player/pagelist?aid=73342471').json()
def download(url):
any_download(url, output_dir='video', merge='merge')
for i,video_content in enumerate(res_json['data']):
video_name=video_content['part']
video_url='https://www.bilibili.com/video/av73342471'+'?p=%d'%(i+1)
print('视频地址为：',video_url)
print('视频名字为：',video_name)
pool.submit(download, video_url)
pool.shutdown(wait=True)