爬取豆瓣音乐TOP250的数据

参考网址：https://music.douban.com/top250

因为详细页的信息更丰富，本次爬虫在详细页中进行，因此先爬取进入详细页的网址链接，进而爬取数据。

需要爬取的信息有：歌曲名、表演者、流派、发行时间、出版者和评分等。

将数据分别使用TXT、JSON、CSV存储。

import re
import csv
import time
import json
import requests
from bs4 import BeautifulSoup
from requests import RequestException
    
    
def get_one_page(url):
    try:
        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36' 
                   + '(KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36'}
        response = requests.get(url, headers=headers)
        #response.encoding = response.apparent_encoding
        if response.status_code == 200:
            return response.text
        else:
            return None
        return None
    except RequestException:
        return None

def get_detailurl(text):
    detailurl = []
    soup = BeautifulSoup(text, 'lxml')
    nbg = soup.find_all(name='a', class_='nbg')
    for i in nbg:
        detailurl.append(i['href'])
    return detailurl
    
def parse_one_page(text):
    soup = BeautifulSoup(text, 'lxml') #使用lxml XML 解析库
    performer = soup.select('#info > span > span > a')
    #有标签没有属性的情况下用select, 否则用find_all
    song = soup.select('#wrapper > h1 > span')
    
    style = re.findall('流派:</span> (.*?)<br', text, re.S) #.*?非贪婪匹配
    #re.S使.匹配包括换行在内的所有字符
    if len(style) == 0: #有的页面没有流派,用NULL填充
        style.append('NULL')
    publisher = re.findall('出版者:</span> (.*?)?<br', text, re.S)
    if len(publisher) == 0: #有的页面没有出版者,用NULL填充
        publisher.append('NULL')
    pattern = re.compile('发行时间:</span> (.*?)?<br', re.S)
    #compile()讲正则字符串编译成正则对象，方便之后复用
    time = re.findall(pattern, text)
    
    score = soup.find_all(name='strong', class_="ll rating_num")
    #有标签有属性的情况下用find_all
    yield {
        'performer': performer[0].string,
        'song': song[0].string,
        'style': style[0].strip(),
        'time': time[0].strip(),
        'publisher': publisher[0].strip(),
        'score': score[0].string,
    }
        
def write_to_file(content):
    with open('doubanMusicTop250.txt', 'a', encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False)+'\n')
        #dumps将json对象转化为字符串

def write_to_json(content):
    with open('doubanMusicTop250.json', 'a', encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False)+'\n')
        
def write_to_csv(content):
    with open('doubanMusicTop250.csv', 'a', encoding='utf-8') as f:
        fieldnames = ['publisher', 'style', 'song', 'score', 'performer', 'time']
        writer = csv.DictWriter(f, fieldnames=fieldnames)
        writer.writeheader()
        writer.writerows(content)

if __name__ == '__main__':
    url = 'https://music.douban.com/top250?start={}'
    urls = [url.format(page) for page in range(0,256,25)]
    content = []
    for url in urls:
        text1 = get_one_page(url)
        detailurl = get_detailurl(text1)
        for i in detailurl:
            text2 = get_one_page(i)
            for item in parse_one_page(text2):          
                print(item)
                write_to_file(item)            
                content.append(item)
        time.sleep(1)
    write_to_csv(content)
    write_to_json(content)