爬取网易云音乐评论

 上图中，搜索到评论后，在新窗口打开，却是空白页面，所以进行以下几步。

从服务器获取内容有多种方法，最常用的就是get和post, get方法就是直接从服务器获取内容，其参数都在网址的字符串里面；

post的话，需要向服务器提供特定/指定的data服务器才会给你数据。

所以在此次爬虫中，用的既然是POST方法，点击标头(Heades)向下拉，找From data,如下下图所示： 

 

 From Data是我们给服务器的内容，这样服务器验证后才会给我们返回内容。

 第一阶段：

先把评论内容爬下来：

import requests
import bs4
import re
import openpyxl

def open_url(url):
    name_id=url.split("=")[1] #用等号分割，分割后的第2个元素，e.g. https://music.163.com/#/song?id=1368934278,第2个元素是1368934278
    headers={"user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) 
    Chrome/80.0.3987.87 Safari/537.36 SE 2.X MetaSr 1.0'","origin": "https://music.163.com","pragma": "no-cache","referer": "https://music.163.com/song?id={}".format(name_id),"sec-fetch-dest": "empty","sec-fetch-mode": "cors","sec-fetch-site": "same-origin"}
    #上一行的headrs中多传了refer,origin,pragma等参数，以免服务器疑神疑鬼
    params = "rI3bLLAxz/t3/BANZWzk9NULxcbFEs+vEB1/q2416qyrw0UQc+k7iTBJACUFz9/FQiJcd6HYEMCB2s5wz43TeAhlDngWbLWbJlR5dSAhpKve0D6XMoxupTBiUWy7Ayx2nh/9Hv4gdFZp1lJQbtQaKf5YderW5zZMZGLvNYsFlxMLQvU/gkhBROkGVnzS3QKrDhm1IJeSNEKtjLkiZULkUc/IaOeqDdbdiITodDXlo8b6tXQ2TesbTjvTAuZKu2uxtPTYuncrZJdcK/ihYUTPzw=="
    encSecKey="b3ebf54cbc3d8e1277cba213ef5b9562d1cc5f9515e852d5341b7b79ddfe7e65e96f18c22fe629984274d09d419ffc7c796342936c9e8f578ac44dd814fb6b362a02559d834e3e5a382a9f99418997576ad63483e854fce61d188adcd918f3132bea7fb1c5becae800b4a17eb485e13513854cb836df47d31c485048940d28fb"

    data={"params":params,"encSecKey":encSecKey} #此处注意用的paras和encSecKey是传给服务器的验证密钥，每首歌曲的id不同，密钥也不同；所以，以一个初学者的我来说不知道怎么去解决这个问题
    target_url="https://music.163.com/weapi/comment/resource/comments/get?csrf_token="
    res=requests.post(target_url,headers=headers,data=data)
    return res

def find_infor(res):
    soup=bs4.BeautifulSoup(res.text,'html.parser')
    soup.find()




def main():
    url=input("请输入链接地址：")
    res=open_url(url)

    with open("网页初始解析3.txt",'w',encoding='utf-8') as f:
        f.write(res.text)

    # data=find_infor(res
    # to_excel(data)


if __name__=="__main__":
    main()

  

第二阶段：

提取并美化结果　　

 截止到第一阶段，我们爬取到的是一个大的字符串，也即是json的数据；其实看起来就是python的一个字典形式；这里的以文本形式保存的数据结构，是一个大的字符串，这个大的字符串我们称之为json;

json通俗的说是用字符串的形式把python的数据结构给封装起来，操作JSON格式的数据，通常有json.loads和json.dumps方法。

 最外面的一层是{}的明显是json。

import requests
import bs4
import json
import re
import openpyxl

def get_comments(res):
    comments_json = json.loads(res.text)
    comments = comments_json['data']["comments"]
    # with open('comments.txt',"w",encoding="utf-8") as file:
    #     for each in comments:
    #         file.write(each['user']['nickname']+':

')
    #         file.write(each['content']+'
')
    #         file.write("---------------------------------
")
    return comments
def open_url(url):
    name_id=url.split("=")[1] #用等号分割，分割后的第2个元素，e.g. https://music.163.com/#/song?id=1368934278,第2个元素是1368934278
    headers={"user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) 
    Chrome/80.0.3987.87 Safari/537.36 SE 2.X MetaSr 1.0'","origin": "https://music.163.com","pragma": "no-cache","referer": "https://music.163.com/song?id={}".format(name_id),"sec-fetch-dest": "empty","sec-fetch-mode": "cors","sec-fetch-site": "same-origin"}
    #上一行的headrs中多传了refer,origin,pragma等参数，以免服务器疑神疑鬼
    params = "rI3bLLAxz/t3/BANZWzk9NULxcbFEs+vEB1/q2416qyrw0UQc+k7iTBJACUFz9/FQiJcd6HYEMCB2s5wz43TeAhlDngWbLWbJlR5dSAhpKve0D6XMoxupTBiUWy7Ayx2nh/9Hv4gdFZp1lJQbtQaKf5YderW5zZMZGLvNYsFlxMLQvU/gkhBROkGVnzS3QKrDhm1IJeSNEKtjLkiZULkUc/IaOeqDdbdiITodDXlo8b6tXQ2TesbTjvTAuZKu2uxtPTYuncrZJdcK/ihYUTPzw=="
    encSecKey="b3ebf54cbc3d8e1277cba213ef5b9562d1cc5f9515e852d5341b7b79ddfe7e65e96f18c22fe629984274d09d419ffc7c796342936c9e8f578ac44dd814fb6b362a02559d834e3e5a382a9f99418997576ad63483e854fce61d188adcd918f3132bea7fb1c5becae800b4a17eb485e13513854cb836df47d31c485048940d28fb"

    data={"params":params,"encSecKey":encSecKey} #此处注意用的paras和encSecKey是传给服务器的验证密钥，每首歌曲的id不同，密钥也不同；所以，以一个初学者的我来说不知道怎么去解决这个问题
    target_url="https://music.163.com/weapi/comment/resource/comments/get?csrf_token="
    res=requests.post(target_url,headers=headers,data=data)
    return res

def find_infor(res):
    soup=bs4.BeautifulSoup(res.text,'html.parser')
    soup.find()




def main():
    url=input("请输入链接地址：")
    res=open_url(url)
    comments=get_comments(res)
    with open('comments1.txt',"w",encoding="utf-8") as file:
        for each in comments:
            file.write(each['user']['nickname']+':

')
            file.write(each['content']+'
')
            file.write("---------------------------------
")


    # with open("网页初始解析3.txt",'w',encoding='utf-8') as f:
    #     f.write(res.text)

    # data=find_infor(res
    # to_excel(data)

if __name__=="__main__":
    main()

上述有点小问题，只打印了最新的评论，而没有打印精彩评论。

第三阶段继续看：

 第四阶段：

打印了精彩评论但是却没打印，一般评论；

也尝试了，把一般评论和精彩评论合并到一块，但是用append()未成功。

import requests
import bs4
import json
import re
import openpyxl

def get_comments(res):
    comments_json = json.loads(res.text)
    comments = comments_json['data']["comments"]
    comments1 = comments_json['data']['hotComments']
    # comments = comments.append(comments1)
    # with open('comments.txt',"w",encoding="utf-8") as file:
    #     for each in comments:
    #         file.write(each['user']['nickname']+':

')
    #         file.write(each['content']+'
')
    #         file.write("---------------------------------
")
    return comments1
def open_url(url):
    name_id=url.split("=")[1] #用等号分割，分割后的第2个元素，e.g. https://music.163.com/#/song?id=1368934278,第2个元素是1368934278
    headers={"user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) 
    Chrome/80.0.3987.87 Safari/537.36 SE 2.X MetaSr 1.0'","origin": "https://music.163.com","pragma": "no-cache","referer": "https://music.163.com/song?id={}".format(name_id),"sec-fetch-dest": "empty","sec-fetch-mode": "cors","sec-fetch-site": "same-origin"}
    #上一行的headrs中多传了refer,origin,pragma等参数，以免服务器疑神疑鬼

    params = "oDVVbbZOHaFpsRbYsvfTFuwoSFkMd5C/Ne8TuTOoQ1+nuCmBjh9s1vwqDkXwWOd6qqA3nsQ3CV0vYtCN/NRnL0fpoF+xXaPCjwyvlJsP93LWLgNEYhNPtd4gPKEcd4jIxNLm0+7ywkaFSio8x8lS3zVOWUQXeo310FeGkfNg76qZzsjtA5fTIWkT7pCjMnTVMo8UR3mGdbdVgIF7q0cCzBq/wbKo/VytR/BCbMjm033R/ummZFmVwMAw1lL+tdphi25lUooqV1mrosiOZEJRMA=="
    encSecKey = "9c1e8a0c9d5b4ad60ca0ee1e6688ac2a41cef5a3aea003a1d3e79eae42a589ea14f501ac48c8bf29f82f1a3d232f895081920f35e75ef38361afbcd5a4aec7ab91325c155a8195fd1f376410090633648cdeb2e480951f8d4bb78bb870fc8f376442b590dc496dc2f83e58b5be67e0a5450f25edb64175392ea8bd090c188379"

    data={"params":params,"encSecKey":encSecKey} #此处注意用的paras和encSecKey是传给服务器的验证密钥，每首歌曲的id不同，密钥也不同；所以，以一个初学者的我来说不知道怎么去解决这个问题
    target_url="https://music.163.com/weapi/comment/resource/comments/get?csrf_token="
    res=requests.post(target_url,headers=headers,data=data)
    return res

def find_infor(res):
    soup=bs4.BeautifulSoup(res.text,'html.parser')
    soup.find()




def main():
    url=input("请输入链接地址：")
    res=open_url(url)
    comments=get_comments(res)
    print(type(comments)) #可看到comments是list列表
    with open('comments6.txt',"w",encoding="utf-8") as file:
        for each in comments:
            file.write(each['user']['nickname']+':

')
            file.write(each['content']+'
')
            file.write("---------------------------------
")


    # with open("网页初始解析3.txt",'w',encoding='utf-8') as f:
    #     f.write(res.text)

    # data=find_infor(res
    # to_excel(data)

if __name__=="__main__":
    main()

 第五阶段：

搞定

import requests
import bs4
import json
import re
import openpyxl

def get_comments(res):
    comments_json = json.loads(res.text)
    comments1 = comments_json['data']["comments"]
    comments2 = comments_json['data']['hotComments']
    comments3 = comments1+comments2
    # with open('comments.txt',"w",encoding="utf-8") as file:
    #     for each in comments:
    #         file.write(each['user']['nickname']+':

')
    #         file.write(each['content']+'
')
    #         file.write("---------------------------------
")
    return comments3
def open_url(url):
    name_id=url.split("=")[1] #用等号分割，分割后的第2个元素，e.g. https://music.163.com/#/song?id=1368934278,第2个元素是1368934278
    headers={"user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) 
    Chrome/80.0.3987.87 Safari/537.36 SE 2.X MetaSr 1.0'","origin": "https://music.163.com","pragma": "no-cache","referer": "https://music.163.com/song?id={}".format(name_id),"sec-fetch-dest": "empty","sec-fetch-mode": "cors","sec-fetch-site": "same-origin"}
    #上一行的headrs中多传了refer,origin,pragma等参数，以免服务器疑神疑鬼

    params = "oDVVbbZOHaFpsRbYsvfTFuwoSFkMd5C/Ne8TuTOoQ1+nuCmBjh9s1vwqDkXwWOd6qqA3nsQ3CV0vYtCN/NRnL0fpoF+xXaPCjwyvlJsP93LWLgNEYhNPtd4gPKEcd4jIxNLm0+7ywkaFSio8x8lS3zVOWUQXeo310FeGkfNg76qZzsjtA5fTIWkT7pCjMnTVMo8UR3mGdbdVgIF7q0cCzBq/wbKo/VytR/BCbMjm033R/ummZFmVwMAw1lL+tdphi25lUooqV1mrosiOZEJRMA=="
    encSecKey = "9c1e8a0c9d5b4ad60ca0ee1e6688ac2a41cef5a3aea003a1d3e79eae42a589ea14f501ac48c8bf29f82f1a3d232f895081920f35e75ef38361afbcd5a4aec7ab91325c155a8195fd1f376410090633648cdeb2e480951f8d4bb78bb870fc8f376442b590dc496dc2f83e58b5be67e0a5450f25edb64175392ea8bd090c188379"

    data={"params":params,"encSecKey":encSecKey} #此处注意用的paras和encSecKey是传给服务器的验证密钥，每首歌曲的id不同，密钥也不同；所以，以一个初学者的我来说不知道怎么去解决这个问题
    target_url="https://music.163.com/weapi/comment/resource/comments/get?csrf_token="
    res=requests.post(target_url,headers=headers,data=data)
    return res

def find_infor(res):
    soup=bs4.BeautifulSoup(res.text,'html.parser')
    soup.find()




def main():
    url=input("请输入链接地址：")
    res=open_url(url)
    comments=get_comments(res)
    print(type(comments))
    with open('comments7.txt',"w",encoding="utf-8") as file:
        for each in comments:
            file.write(each['user']['nickname']+':

')
            file.write(each['content']+'
')
            file.write("---------------------------------
")


    # with open("网页初始解析3.txt",'w',encoding='utf-8') as f:
    #     f.write(res.text)

    # data=find_infor(res
    # to_excel(data)

if __name__=="__main__":
    main()

# import random
# list1=[1,2,3]
# list2=[4,5,6]
# print(list1,list2,end='
')
# # list3=list1.append(list2)#list1.append(list2)之后list1为空了；
# # list3=list1.extend(list2)#list1.extend(list2)之后list1为空了；
# print(type(list1),list1.append(list2))
# print(type(list2),list1.extend(list2))
# list3=list1+list2
# print(type(list3),list3)

 此外，关于加密部分可参考这两个：https://blog.csdn.net/weixin_44530979/article/details/87925950，https://blog.csdn.net/weixin_40352715/article/details/107879915，写的很好。