猫眼电影top100抓取案例

最新推荐文章于 2020-04-17 16:52:28 发布

猫小咪编程

最新推荐文章于 2020-04-17 16:52:28 发布

阅读量1.3k

点赞数 3

分类专栏： Python爬虫

本文链接：https://blog.csdn.net/jaffe507/article/details/105421922

版权

Python爬虫专栏收录该内容

7 篇文章 1 订阅

订阅专栏

猫眼电影 - 榜单 - top100榜
电影名称、主演、上映时间

数据抓取实现

1、确定响应内容中是否存在所需数据

右键 - 查看网页源代码 - 搜索关键字 - 存在！！

2、找URL规律

第1页：https://maoyan.com/board/4?offset=0
第2页：https://maoyan.com/board/4?offset=10
第n页：offset=(n-1)*10

3、正则表达式

<div class="movie-item-info">.*?title="(.*?)".*?class="star">(.*?)</p>.*?releasetime">(.*?)</p>

4、编写程序框架，完善程序

from urllib import request
import re
import time
import random
from useragents import ua_list

class MaoyanSpider(object):
  def __init__(self):
    self.url = 'https://maoyan.com/board/4?offset={}'
    # 计数
    self.num = 0

  # 获取
  def get_html(self,url):
    headers = {
      'User-Agent' : random.choice(ua_list)
    }
    req = request.Request(url=url,headers=headers)
    res = request.urlopen(req)
    html = res.read().decode('utf-8')
    # 直接调用解析函数
    self.parse_html(html)

  # 解析
  def parse_html(self,html):
    re_bds = r'<div class="movie-item-info">.*?title="(.*?)".*?class="star">(.*?)</p>.*?releasetime">(.*?)</p>'
    pattern = re.compile(re_bds,re.S)
    # film_list: [('霸王别姬','张国荣','1993'),()]
    film_list = pattern.findall(html)
    # 直接调用写入函数
    self.write_html(film_list)

  def write_html(self,film_list):
    item = {}
    for film in film_list:
      item['name'] = film[0].strip()
      item['star'] = film[1].strip()
      item['time'] = film[2].strip()[5:15]
      print(item)

      self.num += 1

  def main(self):
    for offset in range(0,31,10):
      url = self.url.format(offset)
      self.get_html(url)
      time.sleep(random.randint(1,2))
    print('共抓取数据:',self.num)

if __name__ == '__main__':
  start = time.time()
  spider = MaoyanSpider()
  spider.main()
  end = time.time()
  print('执行时间:%.2f' % (end-start))

数据持久化存储

数据持久化存储 - csv文件

作用

将爬取的数据存放到本地的csv文件中

使用流程

1、导入模块
2、打开csv文件
3、初始化写入对象
4、写入数据(参数为列表)
import csv 

with open('film.csv','w') as f:
    writer = csv.writer(f)
    writer.writerow([])

示例代码

创建 test.csv 文件，在文件中写入数据

# 单行写入（writerow([]))
import csv
with open('test.csv','w',newline='') as f:
	writer = csv.writer(f)
	writer.writerow(['步惊云','36'])
	writer.writerow(['超哥哥','25'])

# 多行写入(writerows([(),(),()]
import csv
with open('test.csv','w',newline='') as f:
	writer = csv.writer(f)
	writer.writerows([('聂风','36'),('秦霜','25'),('孔慈','30')])

猫眼电影数据存入本地 maoyanfilm.csv 文件 - 使用writerow()方法实现

# 存入csv文件 - writerow()
def write_html(self,film_list):
  with open('film.csv','a') as f:
    # 初始化写入对象,注意参数f别忘了
    writer = csv.writer(f)
    for film in film_list:
      L = [
        film[0].strip(),
        film[1].strip(),
        film[2].strip()[5:15]
      ]
      # writerow()参数为列表
      writer.writerow(L)

思考：使用 writerows()方法实现？

# 存入csv文件 - writerows()
def write_html(self,film_list):
  L = []
  with open('film.csv','a') as f:
    # 初始化写入对象,注意参数f别忘了
    writer = csv.writer(f)
    for film in film_list:
      t = (
        film[0].strip(),
        film[1].strip(),
        film[2].strip()[5:15]
      )
      L.append(t)
    # writerows()参数为列表
    writer.writerows(L)

数据持久化存储 - MySQL数据库

1、在数据库中建库建表

# 连接到mysql数据库
mysql -h127.0.0.1 -uroot -p123456
# 建库建表
create database maoyandb charset utf8;
use maoyandb;
create table filmtab(
name varchar(100),
star varchar(300),
time varchar(50)
)charset=utf8;

2、回顾pymysql基本使用

import pymysql

# 创建2个对象
db = pymysql.connect('localhost','root','123456','maoyandb',charset='utf8')
cursor = db.cursor()

# 执行SQL命令并提交到数据库执行
# execute()方法第二个参数为列表传参补位
ins = 'insert into filmtab values(%s,%s,%s)'
cursor.execute(ins,['霸王别姬','张国荣','1993'])
db.commit()

# 关闭
cursor.close()
db.close()

来试试高效的executemany()方法？

import pymysql

# 创建2个对象
db = pymysql.connect('192.168.153.137','tiger','123456','maoyandb',charset='utf8')
cursor = db.cursor()

# 抓取的数据
film_list = [('月光宝盒','周星驰','1994'),('大圣娶亲','周星驰','1994')]

# 执行SQL命令并提交到数据库执行
# execute()方法第二个参数为列表传参补位
cursor.executemany('insert into filmtab values(%s,%s,%s)',film_list)
db.commit()

# 关闭
cursor.close()
db.close()

3、将电影信息存入MySQL数据库（尽量使用executemany方法）

# mysql - executemany([(),(),()])
def write_html(self, film_list):
  L = []
  ins = 'insert into filmtab values(%s,%s,%s)'
  for film in film_list:
    t = (
      film[0].strip(),
      film[1].strip(),
      film[2].strip()[5:15]
    )
    L.append(t)

    self.cursor.executemany(ins, L)
    # 千万别忘了提交到数据库执行
    self.db.commit()

4、做个SQL查询

1、查询20年以前的电影的名字和上映时间
  select name,time from filmtab where time<(now()-interval 20 year);
2、查询1990-2000年的电影名字和上映时间
  select name,time from filmtab where time>='1990-01-01' and time<='2000-12-31';

数据持久化存储 - MongoDB数据库

pymongo操作mongodb数据库

import pymongo

# 1.数据库连接对象
conn=pymongo.MongoClient('localhost',27017)
# 2.库对象
db = conn['库名']
# 3.集合对象
myset = db['集合名']
# 4.插入数据
myset.insert_one({字典})

思考

1、能否到电影详情页把评论抓取下来？
2、能否到电影详情页把电影图片抓取下来？ - 并按照电影名称分别创建文件夹

代码实现

from urllib import request
import re
import time
import random
from useragents import ua_list
import os

class MaoyanSpider(object):
  def __init__(self):
    self.url = 'https://maoyan.com/board/4?offset={}'
    # 计数
    self.num = 0

  # 获取
  def get_html(self,url):
    headers = {
      'User-Agent' : random.choice(ua_list)
    }
    req = request.Request(url=url,headers=headers)
    res = request.urlopen(req)
    html = res.read().decode('utf-8','ignore')

    return html

  def re_func(self,re_bds,html):
    pattern = re.compile(re_bds,re.S)
    r_list = pattern.findall(html)

    return r_list

  # 解析
  def parse_html(self,url):
    re_bds = r'<div class="movie-item-info">.*?href="(.*?)".*?title="(.*?)".*?class="star">(.*?)</p>.*?releasetime">(.*?)</p>'
    # html获取 + re解析
    html = self.get_html(url)
    film_list = self.re_func(re_bds,html)
    # 直接调用写入函数
    self.write_html(film_list)

  def write_html(self,film_list):
    film_dict = {}
    for film in film_list:
      film_dict['name'] = film[1].strip()
      film_dict['star'] = film[2].strip()
      film_dict['time'] = film[3].strip()[5:15]
      two_url = 'https://maoyan.com{}'.format(film[0].strip())
      film_dict['comment'] = self.get_comment(two_url)
      self.save_image(two_url,film)
      print(film_dict)

      self.num += 1

  def get_comment(self,two_url):
    # 获取 + 解析
    html = self.get_html(two_url)
    re_bds = r'<div class="comment-content">(.*?)</div>'
    comment_list = self.re_func(re_bds,html)

    return comment_list

  def save_image(self,two_url,film):
    re_bds = r'<div class="img.*?"><img class="default-img" data-src="(.*?)" alt=""></div>'
    html = self.get_html(two_url)
    img_link_list = self.re_func(re_bds,html)


    for img_link in img_link_list:
      req = request.Request(img_link)
      res = request.urlopen(req)
      html = res.read()
      # 处理文件名
      directory = 'D:\\猫眼\\{}\\'.format(film[1].strip())
      if not os.path.exists(directory):
        os.makedirs(directory)

      filename=directory + img_link.split('/')[-1].split('@')[0]
      with open(filename,'wb') as f:
        f.write(html)


  # 入口函数
  def run(self):
    for offset in range(0,31,10):
      url = self.url.format(offset)
      self.parse_html(url)
      time.sleep(random.randint(1,2))
    print('共抓取数据:',self.num)

if __name__ == '__main__':
  start = time.time()
  spider = MaoyanSpider()
  spider.run()
  end = time.time()
  print('执行时间:%.2f' % (end-start))