爬取豆瓣电影TOP 250

网址https://movie.douban.com/top250

image.png

分析url，将首页url按照格式修改https://movie.douban.com/top250?start=0&filter=也可以访问，既可以构造url

image.png

前5页

urls=['https://movie.douban.com/top250?start={}&filter='.format(i)  for in in range(0,125,25)]

爬取每个电影详情页链接，详情页有关于电影的更多信息

def get_url(url):
    html=requests.get(url,headers=headers)
    xdata=etree.HTML(html.text)
    moive_urls=xdata.xpath('//div[@class="item"]/div[@class="pic"]/a[1]/@href')
    # print(moive_urls)
    for moive_url  in moive_urls:   
        get_info(moive_url)       #调用get_info

image.png

在mysql中选择一个库并创建存储数据的格式表（数据库命令）

create table dbmoives(
    id int auto_increment primary  key,
    name text,
    year text,
    director text,
    actor text,
    style text,
    country text,
    language text,
    release_time text,
    time text,
    other_name text,
    score text) charset=utf8;

表结构

image.png

然后获取电影的详细参数并写入数据库mysql

def get_info(url):
    try:
        html=requests.get(url,headers=headers)
        xdata=etree.HTML(html.text)
        name=xdata.xpath('//div[@id="wrapper"]//h1/span/text()')[0]
        print(name)
        year=xdata.xpath('//div[@id="wrapper"]//h1/span/text()')[1][1:5]
        print(year)
        director=xdata.xpath('//div[@id="info"]/span[1]/span[2]/a/text()')[0]
        print(director)
        actor=xdata.xpath('//div[@id="info"]//span[@class="actor"]//a/text()')[0]  #第一个主演
        print(actor)
        styles=xdata.xpath('//div[@id="info"]//span[@property="v:genre"]/text()')
        style='-'.join(styles)   #将list---》str
        print(style)
        country=re.findall('<span class="pl">制片国家/地区:</span> (.*?)<br/>',html.text,re.S)[0]
        print(country)
        language=re.findall(' <span class="pl">语言:</span> (.*?)<br/>',html.text,re.S)[0].replace(' / ','-')
        print(language)
        release_time=re.findall('<span class="pl">上映日期:</span> <span property="v:initialReleaseDate" content=".*?">(.*?)</span>',html.text,re.S)[0]
        print(release_time)
        time=re.findall('<span class="pl">片长:</span> <span property="v:runtime" content=".*?">(.*?)</span>.*?<br/>',html.text,re.S)[0]
        print(time)
        other_name=re.findall('<span class="pl">又名:</span> (.*?)<br/>',html.text,re.S)[0]
        print(other_name)
        score=xdata.xpath('//div[@id="interest_sectl"]//strong/text()')[0]
        print(score)

        #写入数据库mysql
        # insert_sub='insert into  dbmoives  values(0,'+'"'+str(song_name)+'"'+','+'"'+str(songhref)+'"'+','+'"'+str(songtime)+'"'+')'
        insert_sub='insert into  dbmoives values(0,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)'%('"'+str(name)+'"','"'+str(year)+'"','"'+str(director)+'"','"'+str(actor)+'"','"'+str(style)+'"','"'+str(country)+'"','"'+str(language)+'"','"'+str(release_time)+'"','"'+str(time)+'"','"'+str(other_name)+'"','"'+str(score)+'"')
        # print(insert_sub)
        cursor.execute(insert_sub)
        # cursor.execute("insert into  dbmoives values(0,'泰坦尼克号','1997','詹姆斯','莱昂纳多','剧情','美国','英语','1998','194分钟','铁达尼号','9.4')")

    except Exception as e:
        print(e)

完整代码

import requests
from  lxml  import  etree
import re
import pymysql

# conn=pymysql.connect(host='127.0.0.1',user='root',passwd='123456',db='jt',port=3306,charset='utf-8')
conn=pymysql.connect(
            host='127.0.0.1',
            port=3306,
            db='jt',
            user='root',
            passwd='123456',
            # vharset='utf8'
            )
cursor=conn.cursor()

headers={
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36'
}

#根据每页获取每个电影详细的URL
def get_url(url):
    html=requests.get(url,headers=headers)
    xdata=etree.HTML(html.text)
    moive_urls=xdata.xpath('//div[@class="item"]/div[@class="pic"]/a[1]/@href')
    # print(moive_urls)
    for moive_url  in moive_urls:   
        get_info(moive_url)       #调用get_info
        

#获取电影的详细参数
def get_info(url):
    try:
        html=requests.get(url,headers=headers)
        xdata=etree.HTML(html.text)
        name=xdata.xpath('//div[@id="wrapper"]//h1/span/text()')[0]
        print(name)
        year=xdata.xpath('//div[@id="wrapper"]//h1/span/text()')[1][1:5]
        print(year)
        director=xdata.xpath('//div[@id="info"]/span[1]/span[2]/a/text()')[0]
        print(director)
        actor=xdata.xpath('//div[@id="info"]//span[@class="actor"]//a/text()')[0]  #第一个主演
        print(actor)
        styles=xdata.xpath('//div[@id="info"]//span[@property="v:genre"]/text()')
        style='-'.join(styles)   #将list---》str
        print(style)
        country=re.findall('<span class="pl">制片国家/地区:</span> (.*?)<br/>',html.text,re.S)[0]
        print(country)
        language=re.findall(' <span class="pl">语言:</span> (.*?)<br/>',html.text,re.S)[0].replace(' / ','-')
        print(language)
        release_time=re.findall('<span class="pl">上映日期:</span> <span property="v:initialReleaseDate" content=".*?">(.*?)</span>',html.text,re.S)[0]
        print(release_time)
        time=re.findall('<span class="pl">片长:</span> <span property="v:runtime" content=".*?">(.*?)</span>.*?<br/>',html.text,re.S)[0]
        print(time)
        other_name=re.findall('<span class="pl">又名:</span> (.*?)<br/>',html.text,re.S)[0]
        print(other_name)
        score=xdata.xpath('//div[@id="interest_sectl"]//strong/text()')[0]
        print(score)


        #写入数据库mysql
        # insert_sub='insert into  dbmoives  values(0,'+'"'+str(song_name)+'"'+','+'"'+str(songhref)+'"'+','+'"'+str(songtime)+'"'+')'
        insert_sub='insert into  dbmoives values(0,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)'%('"'+str(name)+'"','"'+str(year)+'"','"'+str(director)+'"','"'+str(actor)+'"','"'+str(style)+'"','"'+str(country)+'"','"'+str(language)+'"','"'+str(release_time)+'"','"'+str(time)+'"','"'+str(other_name)+'"','"'+str(score)+'"')
        # print(insert_sub)
        cursor.execute(insert_sub)
        # cursor.execute("insert into  dbmoives values(0,'泰坦尼克号','1997','詹姆斯','莱昂纳多','剧情','美国','英语','1998','194分钟','铁达尼号','9.4')")

    except Exception as e:
        print(e)

if __name__=="__main__":
    urls=['https://movie.douban.com/top250?start={}&filter='.format(i)  for i in range(0,150,25)]

    for url in urls:
        get_url(url)
        # get_info('https://movie.douban.com/subject/1292722/')
    conn.commit()
    cursor.close()
    conn.close()

效果截图

image.png