Python爬虫学习笔记(三)

Cookies：

以抓取https://www.yaozh.com/为例

Test1（不使用cookies）：

代码：

import urllib.request

# 1.添加URL
url = "https://www.yaozh.com/"

# 2.添加请求头
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36"
}

# 3.构建请求对象
request = urllib.request.Request(url, headers=headers)

# 4.发送请求对象
response = urllib.request.urlopen(request)

# 5.读取数据
data = response.read()

#保存到文件中，验证数据
with open('01cookies.html', 'wb')as f:
    f.write(data)

返回：

此时进入页面显示为游客模式，即未登录状态。

Test2（使用cookies：手动登录）：

在network中查找cookies部分

代码（先登录在抓取）：

"""
    直接获取个人中心的页面
    手动粘贴，复制抓包的cookies
    放在 request请求对象的请求头里面
"""
import urllib.request

# 1.添加URL
url = "https://www.yaozh.com/"

# 2.添加请求头
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36",
    "Cookie": "acw_tc=707c9fc316119925309487503e709498d3fe1f6beb4457b1cb1399958ad4d3; PHPSESSID=bvc8utedu2sljbdb818m4va8q3; _ga=GA1.2.472741825.1611992531; _gid=GA1.2.2079712096.1611992531; yaozh_logintime=1611992697; yaozh_user=1038868%09s1mpL3; yaozh_userId=1038868; yaozh_jobstatus=kptta67UcJieW6zKnFSe2JyYnoaSZ5htnZqdg26qb21rg66flM6bh5%2BscZdyVNaWz9Gwl4Ny2G%2BenofNlKqpl6XKppZVnKmflWlxg2lolJabd519626986447e0E3cd918611D19BBEbmpaamm6HcNiemZtVq56lloN0pG2SaZ%2BGam2SaWucl5ianZiWbIdw4g%3D%3Da9295385d0680617486debd4ce304305; _gat=1; Hm_lpvt_65968db3ac154c3089d7f9a4cbb98c94=1611992698; yaozh_uidhas=1; yaozh_mylogin=1611992704; acw_tc=707c9fc316119925309487503e709498d3fe1f6beb4457b1cb1399958ad4d3; Hm_lvt_65968db3ac154c3089d7f9a4cbb98c94=1611992531%2C1611992638",

}

# 3.构建请求对象
request = urllib.request.Request(url, headers=headers)

# 4.发送请求对象
response = urllib.request.urlopen(request)

# 5.读取数据
data = response.read()

#保存到文件中，验证数据
with open('01cookies2.html', 'wb')as f:
    f.write(data)

先登录再抓取

返回：

此时为登录状态s1mpL3。

Test3（使用cookies：代码登录）：

准备：

1.勾选Preserve Log，用于记录上一次登录

2.根据登录时的数据报，发现发送POST请求

3.登陆之后退出，进入登录页面，检察元素，查找表单各项数据，

代码：

"""
    获取个人页面
    1.代码登录  登陆成功    cookie有效
    2.自动带着cookie 去请求个人中心

    cookiejar：自动保存cookie
"""
import urllib.request
from http import cookiejar
from urllib import parse
# 登陆之前，登录页的网址，https://www.yaozh.com/login，找登录参数

# 后台，根据发送的请求方式来判断，如果是GET，返回登录页面，如果是POST，返回登录结果

#   1.代码登录
# 1.1 登陆的网址
login_url = "https://www.yaozh.com/login"
# 1.2 登陆的参数
login_form_data = {
" username": "s1mpL3",
"pwd": "***************",#个人隐私，代码不予显示
"formhash": "87F6F28A4*",#个人隐私，代码不予显示
"backurl": "https%3A%2F%2Fwww.yaozh.com%2F",
}
# 参数需要转码；POST请求的data要求是bytes乐行
login_str = urllib.parse.urlencode(login_form_data).encode('utf-8')
# 1.3 发送POST登录请求
cookie_jar = cookiejar.CookieJar()
# 定义有添加cookie功能的处理器
cook_handler = urllib.request.HTTPCookieProcessor(cookie_jar)
# 根据处理器 生成openner
openner = urllib.request.build_opener(cook_handler)
# 带着参数，发送POST请求
# 添加请求头
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36"
}
login_request = urllib.request.Request(login_url, headers=headers, data=login_str)
# 如果登陆成功，cookiejar自动保存cookie
openner.open(login_request)

#   2. 代码带着cookie去访问个人中心
center_url = "https://www.yaozh.com/member/"
center_request = urllib.request.Request(center_url, headers=headers)
response = openner.open(center_url)
# bytes --> str
data = response.read().decode()
with open('02cookies.html', 'w', encoding="utf-8")as f:
    f.write(data)

代码登录

返回：

以s1mpL3用户返回

注：

1.cookiejar库的使用

from http import cookiejar
cookiejar.CookieJar()

2.HTTPCookieProcessor()：有cookie功能的处理器

3.代码登录：只需修改用户名和密码

URLError：

urllib.request 提示错误
分为URLError HTTPError
其中HTTPError为URLError的子类

Test：

代码1：

import urllib.request
url = 'http://www.xiaojian.cn' # 假设
response = urllib.request.urlopen(url)

返回1：

部分报错：

raise URLError(err)
urllib.error.URLError: <urlopen error [Errno 11001] getaddrinfo failed>

代码2：

import urllib.request
url = 'https://blog.csdn.net/dQCFKyQDXYm3F8rB0/article/details/1111'
response = urllib.request.urlopen(url)

返回2：

部分报错：

raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 404: Not Found

代码3：

import urllib.request

url = 'https://blog.csdn.net/dQCFKyQDXYm3F8rB0/article/details/1111'
try:
    response = urllib.request.urlopen(url)
except urllib.request.HTTPError as error:
    print(error.code)
except urllib.request.URLError as error:
    print(error)

返回3：

代码4：

import urllib.request

url = 'https://blog.cs1'
try:
    response = urllib.request.urlopen(url)
except urllib.request.HTTPError as error:
    print(error.code)
except urllib.request.URLError as error:
    print(error)

返回4：

Requsets：

准备：

安装第三方模块：

pip install requests

Test1（基本属性：GET）：

代码1（不带请求头）：

import requests

url = "http://www.baidu.com"
response = requests.get(url)

# content属性：返回类型是bytes
data = response.content
print(data)

data1 = response.content.decode('utf-8')
print(type(data1))

# text属性：返回类型是文本str（如果响应内容没有编码，将自行编码，可能出错。因此优先使用content）
data2 = response.text
print(type(data2))

返回1：

代码2（带请求头）：

import requests

class RequestSpider(object):
    def __init__(self):
        url = "https://www.baidu.com/"
        headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36"
        }
        self.response = requests.get(url, headers=headers)

    def run(self):
        data = self.response.content

        # 1.获取请求头
        request_headers1 = self.response.request.headers
        print(request_headers1)

        # 2.获取响应头
        request_headers2 = self.response.headers
        print(request_headers2)

        # 3.获取响应状态码
        code = self.response.status_code
        print(code)

        # 4.获取请求的cookie
        request_cookie = self.response.request._cookies
        print(request_cookie)
        #注：用浏览器进入百度时，可能会有很多cookie，这是浏览器自动添加的，不是服务器给的

        # 5.获取响应的cookie
        response_cookie = self.response.cookies
        print(response_cookie)

RequestSpider().run()

返回：

E:\python\python.exe H:/code/Python爬虫/Day04/03-requests_use2.py

{'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36', 'Accept-Encoding': 'gzip, deflate', 'Accept': '*/*', 'Connection': 'keep-alive'}
{'Bdpagetype': '1', 'Bdqid': '0xe0b22322001a2c4a', 'Cache-Control': 'private', 'Connection': 'keep-alive', 'Content-Encoding': 'gzip', 'Content-Type': 'text/html;charset=utf-8', 'Date': 'Sat, 30 Jan 2021 09:27:06 GMT', 'Expires': 'Sat, 30 Jan 2021 09:26:56 GMT', 'P3p': 'CP=" OTI DSP COR IVA OUR IND COM ", CP=" OTI DSP COR IVA OUR IND COM "', 'Server': 'BWS/1.1', 'Set-Cookie': 'BAIDUID=E577CD647F2B1CA6A7C0F4112781CAF9:FG=1; expires=Thu, 31-Dec-37 23:55:55 GMT; max-age=2147483647; path=/; domain=.baidu.com, BIDUPSID=E577CD647F2B1CA6A7C0F4112781CAF9; expires=Thu, 31-Dec-37 23:55:55 GMT; max-age=2147483647; path=/; domain=.baidu.com, PSTM=1611998826; expires=Thu, 31-Dec-37 23:55:55 GMT; max-age=2147483647; path=/; domain=.baidu.com, BAIDUID=E577CD647F2B1CA65749857950B007E4:FG=1; max-age=31536000; expires=Sun, 30-Jan-22 09:27:06 GMT; domain=.baidu.com; path=/; version=1; comment=bd, BDSVRTM=0; path=/, BD_HOME=1; path=/, H_PS_PSSID=33423_33516_33402_33273_33590_26350_33568; path=/; domain=.baidu.com, BAIDUID_BFESS=E577CD647F2B1CA6A7C0F4112781CAF9:FG=1; Path=/; Domain=baidu.com; Expires=Thu, 31 Dec 2037 23:55:55 GMT; Max-Age=2147483647; Secure; SameSite=None', 'Strict-Transport-Security': 'max-age=172800', 'Traceid': '1611998826055672090616191042239287929930', 'X-Ua-Compatible': 'IE=Edge,chrome=1', 'Transfer-Encoding': 'chunked'}
200
<RequestsCookieJar[]>
<RequestsCookieJar[<Cookie BAIDUID=E577CD647F2B1CA65749857950B007E4:FG=1 for .baidu.com/>, <Cookie BAIDUID_BFESS=E577CD647F2B1CA6A7C0F4112781CAF9:FG=1 for .baidu.com/>, <Cookie BIDUPSID=E577CD647F2B1CA6A7C0F4112781CAF9 for .baidu.com/>, <Cookie H_PS_PSSID=33423_33516_33402_33273_33590_26350_33568 for .baidu.com/>, <Cookie PSTM=1611998826 for .baidu.com/>, <Cookie BDSVRTM=0 for www.baidu.com/>, <Cookie BD_HOME=1 for www.baidu.com/>]>

Process finished with exit code 0

Test2（URL自动转译）：

代码1：

# https://www.baidu.com/s?ie=utf-8&f=8&rsv_bp=1&tn=baidu&wd=%E7%88%AC%E8%99%AB&oq=%2526lt%253BcH0%2520-%2520Nu1L&rsv_pq=d38dc072002f5aef&rsv_t=62dcS%2BcocFsilJnL%2FcjmqGeUvo6S6XMFTiyfxi22AnqTbscZBf6K%2F13WW%2Bo&rqlang=cn&rsv_enter=1&rsv_dl=tb&rsv_sug3=4&rsv_sug1=3&rsv_sug7=100&rsv_sug2=0&rsv_btype=t&inputT=875&rsv_sug4=875
# https://www.baidu.com/s?wd=%E7%88%AC%E8%99%AB

import requests

# 参数自动转译
url = "http://www.baidu.com/s?wd=爬虫"
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36"
}
response = requests.get(url, headers=headers)
data = response.content.decode()
with open('baidu.html', 'w', encoding="utf-8")as f:
    f.write(data)

汉字参数自动转译

返回：

成功返回并生成文件，此时汉字作为参数实现了自动转译。

代码2：

# https://www.baidu.com/s?ie=utf-8&f=8&rsv_bp=1&tn=baidu&wd=%E7%88%AC%E8%99%AB&oq=%2526lt%253BcH0%2520-%2520Nu1L&rsv_pq=d38dc072002f5aef&rsv_t=62dcS%2BcocFsilJnL%2FcjmqGeUvo6S6XMFTiyfxi22AnqTbscZBf6K%2F13WW%2Bo&rqlang=cn&rsv_enter=1&rsv_dl=tb&rsv_sug3=4&rsv_sug1=3&rsv_sug7=100&rsv_sug2=0&rsv_btype=t&inputT=875&rsv_sug4=875
# https://www.baidu.com/s?wd=%E7%88%AC%E8%99%AB

import requests

# 参数自动转译
url = "http://www.baidu.com/s"
parmas = {
    'wd': '爬虫',
}
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36"
}
response = requests.get(url, headers=headers, params=parmas)
data = response.content.decode()
with open('baidu1.html', 'w', encoding="utf-8")as f:
    f.write(data)

字典自动转译

返回：

成功返回并生成文件，此时字典作为参数实现了自动转译。

注：

发送POST请求和添加参数

requests.post(url, data=(参数{})， json=(参数))

Test3（json）：

代码：

# https://www.baidu.com/s?ie=utf-8&f=8&rsv_bp=1&tn=baidu&wd=%E7%88%AC%E8%99%AB&oq=%2526lt%253BcH0%2520-%2520Nu1L&rsv_pq=d38dc072002f5aef&rsv_t=62dcS%2BcocFsilJnL%2FcjmqGeUvo6S6XMFTiyfxi22AnqTbscZBf6K%2F13WW%2Bo&rqlang=cn&rsv_enter=1&rsv_dl=tb&rsv_sug3=4&rsv_sug1=3&rsv_sug7=100&rsv_sug2=0&rsv_btype=t&inputT=875&rsv_sug4=875
# https://www.baidu.com/s?wd=%E7%88%AC%E8%99%AB

import requests
import json

url = "https://api.github.com/user"
#这个网址返回的内容不是HTML，而是标准的json
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36"
}
response = requests.get(url, headers=headers)
# str
data = response.content.decode()
print(data)

# str --> dict
data_dict = json.loads(data)
print(data_dict["message"])

# json()会自动将json字符串转换成Python dict list
data1 = response.json()
print(data1)
print(type(data1))
print(data1["message"])

返回：

E:\python\python.exe H:/code/Python爬虫/Day04/03-requests_use3.py
{
  "message": "Requires authentication",
  "documentation_url": "https://docs.github.com/rest/reference/users#get-the-authenticated-user"
}

Requires authentication
{'message': 'Requires authentication', 'documentation_url': 'https://docs.github.com/rest/reference/users#get-the-authenticated-user'}
<class 'dict'>
Requires authentication

Process finished with exit code 0