Python 爬取张国荣最火的 8 首歌，60000 评论看完泪奔！-CSDN博客

本文链接：https://blog.csdn.net/2401_87018873/article/details/142000062

总共64540条的评论中，出现最多的是“生日快乐”、“哥哥”、“加油”、“你若尚在场”、“新年快乐”和“哥哥，生日快乐”。

640?wx_fmt=png

词云图里很少有“4月1日”、“愚人节”的字眼，这并不是今天去给你评论的人少，而是今天这个日子，实在不适合对你说“快乐”。

来，先给大家看看评论的代码。

# coding:utf-8
import json
import time
import requests
from fake_useragent import UserAgent
import random
import multiprocessing
import sys
#reload(sys)
#sys.setdefaultencoding(‘utf-8’)

ua = UserAgent(verify_ssl=False)

song_list = [{‘186453’:‘春夏秋冬’},{‘188204’:‘沉默是金’},{‘188175’:‘倩女幽魂’},{‘188489’:‘风继续吹’},{‘187374’:‘我’},{‘186760’:‘风雨起时’}]
headers = {
    ‘Origin’:‘https://music.163.com’,
    ‘Referer’: ‘https://music.163.com/song?id=26620756’,
    ‘Host’: ‘music.163.com’,
    ‘User-Agent’: ua.random
}

def get_comments(page,ite):
    # 获取评论信息
    # “”"
    for key, values in ite.items():
        song_id = key
        song_name = values
    ip_list = [IP列表]
    url = ‘http://music.163.com/api/v1/resource/comments/R_SO_4_’+ song_id +‘?limit=20&offset=’ + str(page)
    proxies = get_random_ip(ip_list)
    try:
        response = requests.get(url=url, headers=headers,proxies=proxies)
    except Exception as e:
        print (page)
        print (ite)
        return 0
    result = json.loads(response.text)
    items = result[‘comments’]
    for item in items:
        # 用户名
        user_name = item[‘user’][‘nickname’].replace(‘,’, ‘，’)
        # 用户ID
        user_id = str(item[‘user’][‘userId’])
        print(user_id)
        # 评论内容
        comment = item[‘content’].strip().replace(‘\n’, ‘’).replace(‘,’, ‘，’)
        # 评论ID
        comment_id = str(item[‘commentId’])
        # 评论点赞数
        praise = str(item[‘likedCount’])
        # 评论时间
        date = time.localtime(int(str(item[‘time’])[:10]))
        date = time.strftime(“%Y-%m-%d %H:%M:%S”, date)

八首歌的歌词代码：

import requests
from bs4 import BeautifulSoup
import re
import json
import time
import random
import os

headers = {
    ‘User-Agent’: ‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3355.4 Safari/537.36’,
    ‘Referer’: ‘http://music.163.com’,
    ‘Host’: ‘music.163.com’
}

# 获取页面源码
def GetHtml(url):
    try:
        res = requests.get(url=url, headers=headers)
    except:
        return None
    return res.text

# 提取歌手歌词信息
def GetSongsInfo(url):
    print(‘[INFO]:Getting Songs Info…’)
    html = GetHtml(url)
    soup = BeautifulSoup(html, ‘lxml’)
    links = soup.find(‘ul’, class_=‘f-hide’).find_all(‘a’)
    if len(links) < 1:
        print(‘[Warning]:_GetSongsInfo  not find…’)
    Info = {‘ID’: [], ‘NAME’: []}
    for link in links:
        SongID = link.get(‘href’).split(‘=’)[-1]
        SongName = link.get_text()
        Info[‘ID’].append(SongID)
        Info[‘NAME’].append(SongName)
    # print(Info)
    return Info

def GetLyrics(SongID):
    print(‘[INFO]:Getting %s lyric…’ % SongID)
    ApiUrl = ‘http://music.163.com/api/song/lyric?id={}&lv=1&kv=1&tv=-1’.format(SongID)
    html = GetHtml(ApiUrl)
    html_json = json.loads(html)
    temp = html_json[‘lrc’][‘lyric’]
    rule = re.compile(r’[.*]')
    lyric = re.sub(rule, ‘’, temp).strip()
    print(lyric)
    return lyric

def main():
    SingerId = input(‘Enter the Singer ID:’)
    url = ‘http://music.163.com/artist?id={}’.format(SingerId)
    # url = “http://music.163.com/artist?id=6457”
    Info = GetSongsInfo(url)
    IDs = Info[‘ID’]
    i = 0
    for ID in IDs:
        lyric = GetLyrics(ID)
        SaveLyrics(Info[‘NAME’][i], lyric)
        i += 1
        time.sleep(random.random() * 3)
        # print(‘[INFO]:All Done…’)

def SaveLyrics(SongName, lyric):
    print(‘[INFO]: Start to Save {}…’.format(SongName))
    if not os.path.isdir(‘./results’):
        os.makedirs(‘./results’)
    with open(‘./results/{}.txt’.format(SongName), ‘w’, encoding=‘utf-8’) as f:
        f.write(lyric)

640?wx_fmt=png