回家很久了，实在熬不住，想起来爬点数据玩一玩，之前自己笔记本是win7加ubuntu16.04双系统，本打算在ubuntu里写代码的，可是回到家ubuntu打开一直是紫屏，百度知乎方法用了也没解决，厉害的兄弟可以教下我哦，过年有红包哦！！然后就还是在win7下开始写代码了（电脑太卡，一直不想装Python），今天爬的是豆瓣音乐top250，比较简单，主要是练练手。

代码

import requests

import re

from bs4 import BeautifulSoup

import time

import pymongo



client = pymongo.MongoClient('localhost', 27017)

douban = client['douban']

musictop = douban['musictop']



headers = {

    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'

}

urls = ['https://music.douban.com/top250?start={}'.format(str(i)) for i in range(0,250,25)]



def get_url_music(url):

    wb_data = requests.get(url,headers=headers)

    soup = BeautifulSoup(wb_data.text,'lxml')

    music_hrefs = soup.select('a.nbg')

    for music_href in music_hrefs:

        get_music_info(music_href['href'])

        time.sleep(2)



def get_music_info(url):

    wb_data = requests.get(url,headers=headers)

    soup = BeautifulSoup(wb_data.text,'lxml')

    names = soup.select('h1 > span')

    authors = soup.select('span.pl > a')

    styles = re.findall('<span class="pl">流派:</span>&nbsp;(.*?)<br />',wb_data.text,re.S)

    times = re.findall('<span class="pl">发行时间:</span>&nbsp;(.*?)<br />',wb_data.text,re.S)

    contents = soup.select('span.short > span')

    if len(names) == 0:

        name = '缺失'

    else:

        name = names[0].get_text()

    if len(authors) == 0:

        author = '佚名'

    else:

        author = authors[0].get_text()

    if len(styles) == 0:

        style = '未知'

    else:

        style = styles[0].split('\n')[0]

    if len(times) == 0:

        time = '未知'

    else:

        time = times[0].split('-')[0]

    if len(contents) == 0:

        content = '无'

    else:

        content = contents[0].get_text()

    info = {

        'name':name,

        'author':author,

        'style':style,

        'time':time,

        'content':content

    }

    musictop.insert_one(info)



for url in urls:

    get_url_music(url)

1加了请求头（本来没加，调试几次突然没数据了，加了请求头开始也没好，后来又好了，可能是网络原因）
2这次是进入信息页爬的数据（上次爬电影没采用这种方法，缺少了部分数据）
3数据的预处理用了很多if函数，厉害的兄弟有什么优化的方法。

数据分析

1部分数据可以见上图
2中国音乐作者还是很多的，哈哈。
3随着音乐设备和网络的普及，流行音乐的发展，可以看出2000年后作品越来越多，到2010年又积极下滑（经典就是经典，无法吐槽现在的音乐）
4风格大家可以看出流行，摇滚，民谣占了一大半。
5最后弄了一首周董的《不能说的秘密》做词云，想想小时候都是回忆啊。

问题

import requests

import re

from bs4 import BeautifulSoup

import time

import pymysql



conn = pymysql.connect(host='localhost', user='root', passwd='123456', db='test', port=3306, charset='utf8')

cursor = conn.cursor()



headers = {

    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'

}

urls = ['https://music.douban.com/top250?start={}'.format(str(i)) for i in range(0,225,25)]



def get_url_music(url):

    wb_data = requests.get(url,headers=headers)

    soup = BeautifulSoup(wb_data.text,'lxml')

    music_hrefs = soup.select('a.nbg')

    for music_href in music_hrefs:

        get_music_info(music_href['href'])

        time.sleep(2)



def get_music_info(url):

    wb_data = requests.get(url,headers=headers)

    soup = BeautifulSoup(wb_data.text,'lxml')

    names = soup.select('h1 > span')

    authors = soup.select('span.pl > a')

    styles = re.findall('<span class="pl">流派:</span>&nbsp;(.*?)<br />',wb_data.text,re.S)

    times = re.findall('<span class="pl">发行时间:</span>&nbsp;(.*?)<br />',wb_data.text,re.S)

    contents = soup.select('span.short > span')

    if len(names) == 0:

        name = '缺失'

    else:

        name = names[0].get_text()

    if len(authors) == 0:

        author = '佚名'

    else:

        author = authors[0].get_text()

    if len(styles) == 0:

        style = '未知'

    else:

        style = styles[0].split('\n')[0]

    if len(times) == 0:

        time = '未知'

    else:

        time = times[0].split('-')[0]

    if len(contents) == 0:

        content = '无'

    else:

        content = contents[0].get_text()

    info = {

        'name':name,

        'author':author,

        'style':style,

        'time':time,

        'content':content

    }



    cursor.execute("use test")

    cursor.execute("insert into doubanmusic250 (name,author,style,time,content) values(%s,%s,%s,%s,%s)", (name,author,style,time,content))

    conn.commit()



for url in urls:

    get_url_music(url)

最近再学mysql，想用Python连接MySQL的，可是出错，附上代码，大牛们前来指导。代码出错图：