Python은 댓글이 60,000개가 넘는 Leslie Cheung의 가장 인기 있는 8곡을 크롤링했는데, 읽은 후 눈물이 터졌습니다!

# 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)

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(&#39;[Warning]:_GetSongsInfo <links> not find...&#39;)
    Info = {&#39;ID&#39;: [], &#39;NAME&#39;: []}
    for link in links:
        SongID = link.get(&#39;href&#39;).split(&#39;=&#39;)[-1]
        SongName = link.get_text()
        Info[&#39;ID&#39;].append(SongID)
        Info[&#39;NAME&#39;].append(SongName)
    # print(Info)
    return Info


def GetLyrics(SongID):
    print(&#39;[INFO]:Getting %s lyric...&#39; % SongID)
    ApiUrl = &#39;http://music.163.com/api/song/lyric?id={}&lv=1&kv=1&tv=-1&#39;.format(SongID)
    html = GetHtml(ApiUrl)
    html_json = json.loads(html)
    temp = html_json[&#39;lrc&#39;][&#39;lyric&#39;]
    rule = re.compile(r&#39;\[.*\]&#39;)
    lyric = re.sub(rule, &#39;&#39;, temp).strip()
    print(lyric)
    return lyric


def main():
    SingerId = input(&#39;Enter the Singer ID:&#39;)
    url = &#39;http://music.163.com/artist?id={}&#39;.format(SingerId)
    # url = "http://music.163.com/artist?id=6457"
    Info = GetSongsInfo(url)
    IDs = Info[&#39;ID&#39;]
    i = 0
    for ID in IDs:
        lyric = GetLyrics(ID)
        SaveLyrics(Info[&#39;NAME&#39;][i], lyric)
        i += 1
        time.sleep(random.random() * 3)
        # print(&#39;[INFO]:All Done...&#39;)


def SaveLyrics(SongName, lyric):
    print(&#39;[INFO]: Start to Save {}...&#39;.format(SongName))
    if not os.path.isdir(&#39;./results&#39;):
        os.makedirs(&#39;./results&#39;)
    with open(&#39;./results/{}.txt&#39;.format(SongName), &#39;w&#39;, encoding=&#39;utf-8&#39;) as f:
        f.write(lyric)