python獲取豆瓣高分電影寫入MYSQL+matplotlib簡單可視化

獲取豆瓣高分電影（500部）寫入MySQL數據庫:

我是一名python開發工程師，整理了一套python的學習資料，從基礎的python腳本到web開發、爬蟲、
數據分析、數據可視化、機器學習、面試真題等。想要的可以進羣：688244617免費領取

#-*-coding:UTF-8-*-
import requests
import json
import pymysql
from lxml import etree
 
def GetWriteData(url,num):
    conn = pymysql.connect(host='127.0.0.1', port=3306, user='root', passwd='root', db='mydata')
    cursor = conn.cursor()
    cursor.execute("DROP TABLE IF EXISTS db")  #如果db Base存在則刪除
    cursor.execute('create table db ( id int(5) primary key, pname varchar(255), pf varchar(10) ,plnum int(10),zhpf int(10))')
    i = 0
    while i < num:
        html = requests.get(url + str(i))
        if '異常請求' in html.text:
            print('請求過於頻繁，請稍後再試！')
            break
        text = json.loads(html.text[12:-1])
        i += 20
        print(i,round(i/20))
        for j in text:
            try:
                s = requests.get(j['url'])
            except:
                print('訪問異常')
            else:
                ehtml = etree.HTML(s.text)
                nu = int(''.join(ehtml.xpath('//*[@id="interest_sectl"]/div[1]/div[2]/div/div[2]/a/span/text()')))
            zhpf=round(float(nu /10000 * 0.5)) + round(float(j['rate']) * 2)
            cursor.execute('INSERT INTO db(id,pname,pf,plnum,zhpf) values (%s, %s, %s ,%s,%s) ',[k,j['title'],j['rate'],nu,zhpf])
            cursor.rowcount
            conn.commit()
    cursor.close()
    conn.close()
    print('任務結束。')
 
if __name__ == '__main__':
    url = 'https://movie.douban.com/j/search_subjects?type=movie&tag=豆瓣高分&sort=recommend&page_limit=20&page_start='
    print('開始獲取,請稍候...')
    GetWriteData(url,500)  # 500爲獲取影片數量

matplotlib簡單可視化：

import pymysql
import matplotlib.pyplot as plt
conn = pymysql.connect(host='127.0.0.1', port=3306, user='root', passwd='root', db='mydata',cursorclass = pymysql.cursors.DictCursor)
cursor = conn.cursor()
cursor.execute('select * from mydata.db order by zhpf desc;')
values = cursor.fetchall()
cursor.close()
conn.close()
namedata=[]
zhpf=[]
n=0
for i in values:
    if n>20:break
    namedata.append(i['pname'])
    zhpf.append(i['zhpf'])
    n+=1
plt.rcParams["font.sans-serif"]=["SimHei"]
plt.rcParams["axes.unicode_minus"]=False
plt.barh(y=namedata, width=zhpf, label='綜合評分',color='steelblue', alpha=0.8, height=0.8)
for y, x in enumerate(zhpf):
    plt.text(x+2, y-0.4, '%s' % x, ha='center', va='bottom')
plt.xlabel("分值")
plt.ylabel("片名")
plt.legend()
plt.show()

 以上就是本文的全部內容，覺得文章還不錯的話不妨收藏起來慢慢看，有任何建議或看法歡迎大家在評論區分享討論！