爬取网易云音乐下面的热门评论
2017-09-11 16:20
363 查看
一、运行环境
(1) win10
(2) python 2.7
(3) pycharm
(4) 安装依赖 pip install PyCrypto 等
二、运行源程序
(1)原始版
(2)改进版
# -*- coding: utf-8 -*-
'''
@Description:
网易云音乐评论爬虫,可以完整爬取整个评论
'''
from Crypto.Cipher import AES
import base64
import requests
import json
import codecs
import time
# 头部信息
headers = {
'Host': "music.163.com",
'Accept-Language': "zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3",
'Accept-Encoding': "gzip, deflate",
'Content-Type': "application/x-www-form-urlencoded",
'Cookie': "_ntes_nnid=754361b04b121e078dee797cdb30e0fd,1486026808627; _ntes_nuid=754361b04b121e078dee797cdb30e0fd; JSESSIONID-WYYY=yfqt9ofhY%5CIYNkXW71TqY5OtSZyjE%2FoswGgtl4dMv3Oa7%5CQ50T%2FVaee%2FMSsCifHE0TGtRMYhSPpr20i%5CRO%2BO%2B9pbbJnrUvGzkibhNqw3Tlgn%5Coil%2FrW7zFZZWSA3K9gD77MPSVH6fnv5hIT8ms70MNB3CxK5r3ecj3tFMlWFbFOZmGw%5C%3A1490677541180; _iuqxldmzr_=32; vjuids=c8ca7976.15a029d006a.0.51373751e63af8; vjlast=1486102528.1490172479.21; __gads=ID=a9eed5e3cae4d252:T=1486102537:S=ALNI_Mb5XX2vlkjsiU5cIy91-ToUDoFxIw; vinfo_n_f_l_n3=411a2def7f75a62e.1.1.1486349441669.1486349607905.1490173828142; P_INFO=m15527594439@163.com|1489375076|1|study|00&99|null&null&null#hub&420100#10#0#0|155439&1|study_client|15527594439@163.com; NTES_CMT_USER_INFO=84794134%7Cm155****4439%7Chttps%3A%2F%2Fsimg.ws.126.net%2Fe%2Fimg5.cache.netease.com%2Ftie%2Fimages%2Fyun%2Fphoto_default_62.png.39x39.100.jpg%7Cfalse%7CbTE1NTI3NTk0NDM5QDE2My5jb20%3D; usertrack=c+5+hljHgU0T1FDmA66MAg==; Province=027; City=027; _ga=GA1.2.1549851014.1489469781; __utma=94650624.1549851014.1489469781.1490664577.1490672820.8; __utmc=94650624; __utmz=94650624.1490661822.6.2.utmcsr=baidu|utmccn=(organic)|utmcmd=organic; playerid=81568911; __utmb=94650624.23.10.1490672820",
'Connection': "keep-alive",
'Referer': 'http://music.163.com/'
}
# 设置代理服务器
proxies = {
'http:': 'http://121.232.146.184',
'https:': 'https://144.255.48.197'
}
# offset的取值为:(评论页数-1)*20,total第一页为true,其余页为false
# first_param = '{rid:"", offset:"0", total:"true", limit:"20", csrf_token:""}' # 第一个参数
second_param = "010001" # 第二个参数
# 第三个参数
third_param = "00e0b509f6259df8642dbc35662901477df22677ec152b5ff68ace615bb7b725152b3ab17a876aea8a5aa76d2e417629ec4ee341f56135fccf695280104e0312ecbda92557c93870114af6c9d05c4f7f0c3685b7a46bee255932575cce10b424d813cfe4875d3e82047b97ddef52741d546b8e289dc6935b3ece0462db0a22b8e7"
# 第四个参数
forth_param = "0CoJUm6Qyw8W8jud"
# 获取参数
def get_params(page): # page为传入页数
iv = "0102030405060708"
first_key = forth_param
second_key = 16 * 'F'
if (page == 1): # 如果为第一页
first_param = '{rid:"", offset:"0", total:"true", limit:"20", csrf_token:""}'
h_encText = AES_encrypt(first_param, first_key, iv)
else:
offset = str((page - 1) * 20)
first_param = '{rid:"", offset:"%s", total:"%s", limit:"20", csrf_token:""}' % (offset, 'false')
h_encText = AES_encrypt(first_param, first_key, iv)
h_encText = AES_encrypt(h_encText, second_key, iv)
return h_encText
# 获取 encSecKey
def get_encSecKey():
encSecKey = "257348aecb5e556c066de214e531faadd1c55d814f9be95fd06d6bff9f4c7a41f831f6394d5a3fd2e3881736d94a02ca919d952872e7d0a50ebfa1769a7a62d512f5f1ca21aec60bc3819a9c3ffca5eca9a0dba6d6f7249b06f5965ecfff3695b54e1c28f3f624750ed39e7de08fc8493242e26dbc4484a01c76f739e135637c"
return encSecKey
# 解密过程
def AES_encrypt(text, key, iv):
pad = 16 - len(text) % 16
text = text + pad * chr(pad)
encryptor = AES.new(key, AES.MODE_CBC, iv)
encrypt_text = encryptor.encrypt(text)
encrypt_text = base64.b64encode(encrypt_text)
return encrypt_text
# 获得评论json数据
def get_json(url, params, encSecKey):
data = {
"params": params,
"encSecKey": encSecKey
}
response = requests.post(url, headers=headers, data=data, proxies=proxies)
return response.content
# 抓取热门评论,返回热评列表
def get_hot_comments(url):
hot_comments_list = []
hot_comments_list.append(u"用户ID 用户昵称 用户头像地址 评论时间 点赞总数 评论内容\n")
params = get_params(1) # 第一页
encSecKey = get_encSecKey()
json_text = get_json(url, params, encSecKey)
json_dict = json.loads(json_text)
hot_comments = json_dict['hotComments'] # 热门评论
print("共有%d条热门评论!" % len(hot_comments))
for item in hot_comments:
comment = item['content'] # 评论内容
likedCount = item['likedCount'] # 点赞总数
comment_time = item['time'] # 评论时间(时间戳)
userID = item['user']['userID'] # 评论者id
nickname = item['user']['nickname'] # 昵称
avatarUrl = item['user']['avatarUrl'] # 头像地址
comment_info = userID + " " + nickname + " " + avatarUrl + " " + comment_time + " " + likedCount + " " + comment + u"\n"
hot_comments_list.append(comment_info)
return hot_comments_list
# 抓取某一首歌的全部评论
def get_all_comments(url):
all_comments_list = [] # 存放所有评论
all_comments_list.append(u"用户ID 用户昵称 用户头像地址 评论时间 点赞总数 评论内容\n") # 头部信息
params = get_params(1)
encSecKey = get_encSecKey()
json_text = get_json(url, params, encSecKey)
json_dict = json.loads(json_text)
comments_num = int(json_dict['total'])
if (comments_num % 20 == 0):
page = comments_num / 20
else:
page = int(comments_num / 20) + 1
print("共有%d页评论!" % page)
for i in range(page): # 逐页抓取,但是由于页数太多了导致连接中断,所以取了部分页数的评论作为参考
params = get_params(i + 1)
encSecKey = get_encSecKey()
json_text = get_json(url, params, encSecKey)
json_dict = json.loads(json_text)
if i == 0:
print("共有%d条评论!" % comments_num) # 全部评论总数
for item in json_dict['comments']:
comment = item['content'] # 评论内容
likedCount = item['likedCount'] # 点赞总数
comment_time = item['time'] # 评论时间(时间戳)
userID = item['user']['userId'] # 评论者id
nickname = item['user']['nickname'] # 昵称
avatarUrl = item['user']['avatarUrl'] # 头像地址
comment_info = unicode(userID) + u" " + nickname + u" " + avatarUrl + u" " + unicode(
comment_time) + u" " + unicode(likedCount) + u" " + comment + u"\n"
all_comments_list.append(comment_info)
print("第%d页抓取完毕!" % (i + 1))
return all_comments_list
# 将评论写入文本文件
def save_to_file(list, filename):
with codecs.open(filename, 'a', encoding='utf-8') as f:
f.writelines(list)
print("写入文件成功!")
if __name__ == "__main__":
while True:
start_time = time.time() # 开始时间
#song_id=418603077 #每个歌曲都有一个id
song_id = input('please input song_id:')
url = "http://music.163.com/weapi/v1/resource/comments/R_SO_4_%s/?csrf_token="%(song_id,)
filename = u"%s.txt"%(song_id)
all_comments_list = get_all_comments(url)
save_to_file(all_comments_list, filename)
end_time = time.time() # 结束时间
print("程序耗时%f秒." % (end_time - start_time))
三、运行结果
(1) win10
(2) python 2.7
(3) pycharm
(4) 安装依赖 pip install PyCrypto 等
二、运行源程序
(1)原始版
# -*- coding: utf-8 -*- # <a href="http://www.jobbole.com/members/dai745726163">@Time</a> ''' @Description: 网易云音乐评论爬虫,可以完整爬取整个评论 部分参考了@平胸小仙女的文章(地址:https://www.zhihu.com/question/36081767) post加密部分也给出了,可以参考原帖: 作者:平胸小仙女 链接:https://www.zhihu.com/question/36081767/answer/140287795 来源:知乎 ''' from Crypto.Cipher import AES import base64 import requests import json import codecs import time # 头部信息 headers = { 'Host': "music.163.com", 'Accept-Language': "zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3", 'Accept-Encoding': "gzip, deflate", 'Content-Type': "application/x-www-form-urlencoded", 'Cookie': "_ntes_nnid=754361b04b121e078dee797cdb30e0fd,1486026808627; _ntes_nuid=754361b04b121e078dee797cdb30e0fd; JSESSIONID-WYYY=yfqt9ofhY%5CIYNkXW71TqY5OtSZyjE%2FoswGgtl4dMv3Oa7%5CQ50T%2FVaee%2FMSsCifHE0TGtRMYhSPpr20i%5CRO%2BO%2B9pbbJnrUvGzkibhNqw3Tlgn%5Coil%2FrW7zFZZWSA3K9gD77MPSVH6fnv5hIT8ms70MNB3CxK5r3ecj3tFMlWFbFOZmGw%5C%3A1490677541180; _iuqxldmzr_=32; vjuids=c8ca7976.15a029d006a.0.51373751e63af8; vjlast=1486102528.1490172479.21; __gads=ID=a9eed5e3cae4d252:T=1486102537:S=ALNI_Mb5XX2vlkjsiU5cIy91-ToUDoFxIw; vinfo_n_f_l_n3=411a2def7f75a62e.1.1.1486349441669.1486349607905.1490173828142; P_INFO=m15527594439@163.com|1489375076|1|study|00&99|null&null&null#hub&420100#10#0#0|155439&1|study_client|15527594439@163.com; NTES_CMT_USER_INFO=84794134%7Cm155****4439%7Chttps%3A%2F%2Fsimg.ws.126.net%2Fe%2Fimg5.cache.netease.com%2Ftie%2Fimages%2Fyun%2Fphoto_default_62.png.39x39.100.jpg%7Cfalse%7CbTE1NTI3NTk0NDM5QDE2My5jb20%3D; usertrack=c+5+hljHgU0T1FDmA66MAg==; Province=027; City=027; _ga=GA1.2.1549851014.1489469781; __utma=94650624.1549851014.1489469781.1490664577.1490672820.8; __utmc=94650624; __utmz=94650624.1490661822.6.2.utmcsr=baidu|utmccn=(organic)|utmcmd=organic; playerid=81568911; __utmb=94650624.23.10.1490672820", 'Connection': "keep-alive", 'Referer': 'http://music.163.com/' } # 设置代理服务器 proxies = { 'http:': 'http://121.232.146.184', 'https:': 'https://144.255.48.197' } # offset的取值为:(评论页数-1)*20,total第一页为true,其余页为false # first_param = '{rid:"", offset:"0", total:"true", limit:"20", csrf_token:""}' # 第一个参数 second_param = "010001" # 第二个参数 # 第三个参数 third_param = "00e0b509f6259df8642dbc35662901477df22677ec152b5ff68ace615bb7b725152b3ab17a876aea8a5aa76d2e417629ec4ee341f56135fccf695280104e0312ecbda92557c93870114af6c9d05c4f7f0c3685b7a46bee255932575cce10b424d813cfe4875d3e82047b97ddef52741d546b8e289dc6935b3ece0462db0a22b8e7" # 第四个参数 forth_param = "0CoJUm6Qyw8W8jud" # 获取参数 def get_params(page): # page为传入页数 iv = "0102030405060708" first_key = forth_param second_key = 16 * 'F' if (page == 1): # 如果为第一页 first_param = '{rid:"", offset:"0", total:"true", limit:"20", csrf_token:""}' h_encText = AES_encrypt(first_param, first_key, iv) else: offset = str((page - 1) * 20) first_param = '{rid:"", offset:"%s", total:"%s", limit:"20", csrf_token:""}' % (offset, 'false') h_encText = AES_encrypt(first_param, first_key, iv) h_encText = AES_encrypt(h_encText, second_key, iv) return h_encText # 获取 encSecKey def get_encSecKey(): encSecKey = "257348aecb5e556c066de214e531faadd1c55d814f9be95fd06d6bff9f4c7a41f831f6394d5a3fd2e3881736d94a02ca919d952872e7d0a50ebfa1769a7a62d512f5f1ca21aec60bc3819a9c3ffca5eca9a0dba6d6f7249b06f5965ecfff3695b54e1c28f3f624750ed39e7de08fc8493242e26dbc4484a01c76f739e135637c" return encSecKey # 解密过程 def AES_encrypt(text, key, iv): pad = 16 - len(text) % 16 text = text + pad * chr(pad) encryptor = AES.new(key, AES.MODE_CBC, iv) encrypt_text = encryptor.encrypt(text) encrypt_text = base64.b64encode(encrypt_text) return encrypt_text # 获得评论json数据 def get_json(url, params, encSecKey): data = { "params": params, "encSecKey": encSecKey } response = requests.post(url, headers=headers, data=data, proxies=proxies) return response.content # 抓取热门评论,返回热评列表 def get_hot_comments(url): hot_comments_list = [] hot_comments_list.append(u"用户ID 用户昵称 用户头像地址 评论时间 点赞总数 评论内容\n") params = get_params(1) # 第一页 encSecKey = get_encSecKey() json_text = get_json(url, params, encSecKey) json_dict = json.loads(json_text) hot_comments = json_dict['hotComments'] # 热门评论 print("共有%d条热门评论!" % len(hot_comments)) for item in hot_comments: comment = item['content'] # 评论内容 likedCount = item['likedCount'] # 点赞总数 comment_time = item['time'] # 评论时间(时间戳) userID = item['user']['userID'] # 评论者id nickname = item['user']['nickname'] # 昵称 avatarUrl = item['user']['avatarUrl'] # 头像地址 comment_info = userID + " " + nickname + " " + avatarUrl + " " + comment_time + " " + likedCount + " " + comment + u"\n" hot_comments_list.append(comment_info) return hot_comments_list # 抓取某一首歌的全部评论 def get_all_comments(url): all_comments_list = [] # 存放所有评论 all_comments_list.append(u"用户ID 用户昵称 用户头像地址 评论时间 点赞总数 评论内容\n") # 头部信息 params = get_params(1) encSecKey = get_encSecKey() json_text = get_json(url, params, encSecKey) json_dict = json.loads(json_text) comments_num = int(json_dict['total']) if (comments_num % 20 == 0): page = comments_num / 20 else: page = int(comments_num / 20) + 1 print("共有%d页评论!" % page) for i in range(page-87000): # 逐页抓取 params = get_params(i + 1) encSecKey = get_encSecKey() json_text = get_json(url, params, encSecKey) json_dict = json.loads(json_text) if i == 0: print("共有%d条评论!" % comments_num) # 全部评论总数 for item in json_dict['comments']: comment = item['content'] # 评论内容 likedCount = item['likedCount'] # 点赞总数 comment_time = item['time'] # 评论时间(时间戳) userID = item['user']['userId'] # 评论者id nickname = item['user']['nickname'] # 昵称 avatarUrl = item['user']['avatarUrl'] # 头像地址 comment_info = unicode(userID) + u" " + nickname + u" " + avatarUrl + u" " + unicode( comment_time) + u" " + unicode(likedCount) + u" " + comment + u"\n" all_comments_list.append(comment_info) print("第%d页抓取完毕!" % (i + 1)) return all_comments_list # 将评论写入文本文件 def save_to_file(list, filename): with codecs.open(filename, 'a', encoding='utf-8') as f: f.writelines(list) print("写入文件成功!") if __name__ == "__main__": start_time = time.time() # 开始时间 url = "http://music.163.com/weapi/v1/resource/comments/R_SO_4_186016/?csrf_token=" filename = u"晴天.txt" all_comments_list = get_all_comments(url) save_to_file(all_comments_list, filename) end_time = time.time() # 结束时间 print("程序耗时%f秒." % (end_time - start_time))
(2)改进版
# -*- coding: utf-8 -*-
'''
@Description:
网易云音乐评论爬虫,可以完整爬取整个评论
'''
from Crypto.Cipher import AES
import base64
import requests
import json
import codecs
import time
# 头部信息
headers = {
'Host': "music.163.com",
'Accept-Language': "zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3",
'Accept-Encoding': "gzip, deflate",
'Content-Type': "application/x-www-form-urlencoded",
'Cookie': "_ntes_nnid=754361b04b121e078dee797cdb30e0fd,1486026808627; _ntes_nuid=754361b04b121e078dee797cdb30e0fd; JSESSIONID-WYYY=yfqt9ofhY%5CIYNkXW71TqY5OtSZyjE%2FoswGgtl4dMv3Oa7%5CQ50T%2FVaee%2FMSsCifHE0TGtRMYhSPpr20i%5CRO%2BO%2B9pbbJnrUvGzkibhNqw3Tlgn%5Coil%2FrW7zFZZWSA3K9gD77MPSVH6fnv5hIT8ms70MNB3CxK5r3ecj3tFMlWFbFOZmGw%5C%3A1490677541180; _iuqxldmzr_=32; vjuids=c8ca7976.15a029d006a.0.51373751e63af8; vjlast=1486102528.1490172479.21; __gads=ID=a9eed5e3cae4d252:T=1486102537:S=ALNI_Mb5XX2vlkjsiU5cIy91-ToUDoFxIw; vinfo_n_f_l_n3=411a2def7f75a62e.1.1.1486349441669.1486349607905.1490173828142; P_INFO=m15527594439@163.com|1489375076|1|study|00&99|null&null&null#hub&420100#10#0#0|155439&1|study_client|15527594439@163.com; NTES_CMT_USER_INFO=84794134%7Cm155****4439%7Chttps%3A%2F%2Fsimg.ws.126.net%2Fe%2Fimg5.cache.netease.com%2Ftie%2Fimages%2Fyun%2Fphoto_default_62.png.39x39.100.jpg%7Cfalse%7CbTE1NTI3NTk0NDM5QDE2My5jb20%3D; usertrack=c+5+hljHgU0T1FDmA66MAg==; Province=027; City=027; _ga=GA1.2.1549851014.1489469781; __utma=94650624.1549851014.1489469781.1490664577.1490672820.8; __utmc=94650624; __utmz=94650624.1490661822.6.2.utmcsr=baidu|utmccn=(organic)|utmcmd=organic; playerid=81568911; __utmb=94650624.23.10.1490672820",
'Connection': "keep-alive",
'Referer': 'http://music.163.com/'
}
# 设置代理服务器
proxies = {
'http:': 'http://121.232.146.184',
'https:': 'https://144.255.48.197'
}
# offset的取值为:(评论页数-1)*20,total第一页为true,其余页为false
# first_param = '{rid:"", offset:"0", total:"true", limit:"20", csrf_token:""}' # 第一个参数
second_param = "010001" # 第二个参数
# 第三个参数
third_param = "00e0b509f6259df8642dbc35662901477df22677ec152b5ff68ace615bb7b725152b3ab17a876aea8a5aa76d2e417629ec4ee341f56135fccf695280104e0312ecbda92557c93870114af6c9d05c4f7f0c3685b7a46bee255932575cce10b424d813cfe4875d3e82047b97ddef52741d546b8e289dc6935b3ece0462db0a22b8e7"
# 第四个参数
forth_param = "0CoJUm6Qyw8W8jud"
# 获取参数
def get_params(page): # page为传入页数
iv = "0102030405060708"
first_key = forth_param
second_key = 16 * 'F'
if (page == 1): # 如果为第一页
first_param = '{rid:"", offset:"0", total:"true", limit:"20", csrf_token:""}'
h_encText = AES_encrypt(first_param, first_key, iv)
else:
offset = str((page - 1) * 20)
first_param = '{rid:"", offset:"%s", total:"%s", limit:"20", csrf_token:""}' % (offset, 'false')
h_encText = AES_encrypt(first_param, first_key, iv)
h_encText = AES_encrypt(h_encText, second_key, iv)
return h_encText
# 获取 encSecKey
def get_encSecKey():
encSecKey = "257348aecb5e556c066de214e531faadd1c55d814f9be95fd06d6bff9f4c7a41f831f6394d5a3fd2e3881736d94a02ca919d952872e7d0a50ebfa1769a7a62d512f5f1ca21aec60bc3819a9c3ffca5eca9a0dba6d6f7249b06f5965ecfff3695b54e1c28f3f624750ed39e7de08fc8493242e26dbc4484a01c76f739e135637c"
return encSecKey
# 解密过程
def AES_encrypt(text, key, iv):
pad = 16 - len(text) % 16
text = text + pad * chr(pad)
encryptor = AES.new(key, AES.MODE_CBC, iv)
encrypt_text = encryptor.encrypt(text)
encrypt_text = base64.b64encode(encrypt_text)
return encrypt_text
# 获得评论json数据
def get_json(url, params, encSecKey):
data = {
"params": params,
"encSecKey": encSecKey
}
response = requests.post(url, headers=headers, data=data, proxies=proxies)
return response.content
# 抓取热门评论,返回热评列表
def get_hot_comments(url):
hot_comments_list = []
hot_comments_list.append(u"用户ID 用户昵称 用户头像地址 评论时间 点赞总数 评论内容\n")
params = get_params(1) # 第一页
encSecKey = get_encSecKey()
json_text = get_json(url, params, encSecKey)
json_dict = json.loads(json_text)
hot_comments = json_dict['hotComments'] # 热门评论
print("共有%d条热门评论!" % len(hot_comments))
for item in hot_comments:
comment = item['content'] # 评论内容
likedCount = item['likedCount'] # 点赞总数
comment_time = item['time'] # 评论时间(时间戳)
userID = item['user']['userID'] # 评论者id
nickname = item['user']['nickname'] # 昵称
avatarUrl = item['user']['avatarUrl'] # 头像地址
comment_info = userID + " " + nickname + " " + avatarUrl + " " + comment_time + " " + likedCount + " " + comment + u"\n"
hot_comments_list.append(comment_info)
return hot_comments_list
# 抓取某一首歌的全部评论
def get_all_comments(url):
all_comments_list = [] # 存放所有评论
all_comments_list.append(u"用户ID 用户昵称 用户头像地址 评论时间 点赞总数 评论内容\n") # 头部信息
params = get_params(1)
encSecKey = get_encSecKey()
json_text = get_json(url, params, encSecKey)
json_dict = json.loads(json_text)
comments_num = int(json_dict['total'])
if (comments_num % 20 == 0):
page = comments_num / 20
else:
page = int(comments_num / 20) + 1
print("共有%d页评论!" % page)
for i in range(page): # 逐页抓取,但是由于页数太多了导致连接中断,所以取了部分页数的评论作为参考
params = get_params(i + 1)
encSecKey = get_encSecKey()
json_text = get_json(url, params, encSecKey)
json_dict = json.loads(json_text)
if i == 0:
print("共有%d条评论!" % comments_num) # 全部评论总数
for item in json_dict['comments']:
comment = item['content'] # 评论内容
likedCount = item['likedCount'] # 点赞总数
comment_time = item['time'] # 评论时间(时间戳)
userID = item['user']['userId'] # 评论者id
nickname = item['user']['nickname'] # 昵称
avatarUrl = item['user']['avatarUrl'] # 头像地址
comment_info = unicode(userID) + u" " + nickname + u" " + avatarUrl + u" " + unicode(
comment_time) + u" " + unicode(likedCount) + u" " + comment + u"\n"
all_comments_list.append(comment_info)
print("第%d页抓取完毕!" % (i + 1))
return all_comments_list
# 将评论写入文本文件
def save_to_file(list, filename):
with codecs.open(filename, 'a', encoding='utf-8') as f:
f.writelines(list)
print("写入文件成功!")
if __name__ == "__main__":
while True:
start_time = time.time() # 开始时间
#song_id=418603077 #每个歌曲都有一个id
song_id = input('please input song_id:')
url = "http://music.163.com/weapi/v1/resource/comments/R_SO_4_%s/?csrf_token="%(song_id,)
filename = u"%s.txt"%(song_id)
all_comments_list = get_all_comments(url)
save_to_file(all_comments_list, filename)
end_time = time.time() # 结束时间
print("程序耗时%f秒." % (end_time - start_time))
三、运行结果
相关文章推荐
- 使用爬虫抓取网易云音乐热门评论生成好玩的词云
- Python3实战之爬虫抓取网易云音乐的热门评论
- Python 获取 网易云音乐热门评论
- 带你写爬虫(python)第二篇----抓取网易云音乐下面的评论(API方式)
- python爬虫----网易云音乐之热门评论
- 抓取网易云音乐歌曲热门评论生成词云
- Python 获取 网易云音乐热门评论(python2/python3代码)
- Python爬取网易云音乐热门评论
- 抓取网易云音乐歌曲热门评论生成词云(转)
- Python分析网易云音乐近5年热门歌单
- python爬虫入门 实战(四)---爬“榜姐”话题微博及热门评论
- Scrapy爬取网易云音乐和评论(一、思路分析)
- 新浪微博热门评论抽取规则
- Scrapy爬取网易云音乐和评论(二、Scrapy框架每个模块的作用)
- 新浪微博热门评论爬虫采集
- 如何在node节点的评论下面添加想要…
- 随笔 - 58 文章 - 61 评论 - 7 STM32 端口复用&重映射(USART Remap) 下面跟大家说一下STM32单片机的端口重映射,因为是以
- Scrapy爬取网易云音乐和评论(五、评论)
- [置顶] 网易云音乐评论生成Wordcloud(词云)