python 爬取 豆瓣电影top250 存储到mysql

数据分析师

想在本地找一些开源bi做一些数据可视化的呈现

先在网上扒拉点数据，存储到了本地

主要是学习学习python的爬虫

先在本地建了mysql的表 （比较粗暴）

CREATE TABLE `doubanmovie` (
  `id` int(11) NOT NULL AUTO_INCREMENT,
  `name` text COMMENT ‘电影名称‘,
  `director` text COMMENT ‘导演‘,
  `actor` text COMMENT ‘演员‘,
  `style` text COMMENT ‘风格‘,
  `country` text COMMENT ‘国家‘,
  `release_time` text COMMENT ‘上映日期‘,
  `time` text COMMENT ‘时长‘,
  `score` text COMMENT ‘评分‘,
  PRIMARY KEY (`id`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8;

然后根据学习的整了点数据存入

import requests
from lxml import etree
import re
import pymysql
import time

author = ‘qewwc‘

conn = pymysql.connect(host=‘localhost‘, user=‘root‘, passwd=‘root‘, db=‘test‘, charset="utf8", use_unicode="True",port=3306)
cursor = conn.cursor()

headers = {
    ‘User-Agent‘ :‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36‘
}

sql_in = ‘‘‘insert into doubanmovie (name,director,actor,style,country,release_time,time,score) value (%s,%s,%s,%s,%s,%s,%s,%s)‘‘‘

def get_movie_url(url): # 获取每个电影的链接
    html = requests.get(url=url,headers=headers)
    selector = etree.HTML(html.text)
    movie_hrefs = selector.xpath(‘//div[@class="hd"]/a/@href‘)
    for movie_href in movie_hrefs:
        get_movie_info(movie_href)

def get_movie_info(url):
    html = requests.get(url= url,headers = headers) # <Response [200]>
    selector = etree.HTML(html.text) # <Element html at 0x20892e10108>
    try:
        name = selector.xpath(‘//*[@id="content"]/h1/span[1]/text()‘)[0]
    except IndexError:
        name = ‘‘
    try:
        director = selector.xpath(‘//*[@id="info"]/span[1]/span[2]/a/text()‘)[0]
    except IndexError:
        director = ‘‘
    try:
        actors = selector.xpath(‘//*[@class="actor"]/span[2]‘)[0]
        actor = actors.xpath(‘string(.)‘)
        # actors = re.findall(‘<a href="/.*?/" rel="v:starring">(.*?)</a>‘,html.text,re.S)
    except IndexError:
        actor = ‘‘
    try:
        style = re.findall(‘<span property="v:genre">(.*?)</span>‘, html.text, re.S)[0]
    except IndexError:
        style = ‘‘
    try:
        country = re.findall(‘<span class="pl">制片国家/地区:</span> (.*?)<br/>‘, html.text, re.S)[0]
    except IndexError:
        country = ‘‘
    try:
        release_time = re.findall(‘<span property="v:initialReleaseDate" content=.*?>(.*?)</span>‘, html.text, re.S)[0]
    except IndexError:
        release_time = ‘‘
    try:
        time = re.findall(‘<span property="v:runtime" content=.*?>(.*?)</span>‘, html.text, re.S)[0]
    except IndexError:
        time = ‘‘
    try:
        score = selector.xpath(‘//*[@id="interest_sectl"]/div[1]/div[2]/strong/text()‘)[0]
    except IndexError:
        score = ‘‘
    cursor.execute(
        sql_in,[str(name),str(director),str(actor),str(style),str(country),str(release_time),str(time),str(score)]
    )

# url = ‘https://movie.douban.com/subject/33967902/‘

# <span property="v:initialReleaseDate" content="2019-06-03(英国)">2019-06-03(英国)</span>

urls = [‘https://movie.douban.com/top250?start={}&filter=‘.format(i) for i in range(0,250,25)]
for url in urls:
    get_movie_url(url)
    time.sleep(5)
    print(‘我好了！‘)
conn.commit()

最终数据如下

done！

mzz...