python爬蟲貓眼電影和電影天堂數(shù)據(jù)csv和mysql存儲(chǔ)過程解析

更新時(shí)間：2019年09月05日 09:06:22 作者：凌逆戰(zhàn)

這篇文章主要介紹了python爬蟲貓眼電影和電影天堂數(shù)據(jù)csv和mysql存儲(chǔ)過程解析,文中通過示例代碼介紹的非常詳細(xì)，對(duì)大家的學(xué)習(xí)或者工作具有一定的參考學(xué)習(xí)價(jià)值,需要的朋友可以參考下

字符串常用方法

# 去掉左右空格
'hello world'.strip()  # 'hello world'
# 按指定字符切割
'hello world'.split(' ') # ['hello','world']
# 替換指定字符串
'hello world'.replace(' ','#') # 'hello#world'

csv模塊

作用：將爬取的數(shù)據(jù)存放到本地的csv文件中

使用流程

導(dǎo)入模塊
打開csv文件
初始化寫入對(duì)象
寫入數(shù)據(jù)(參數(shù)為列表)

import csv
with open('test.csv','w') as f: 
 writer = csv.writer(f) # 初始化寫入對(duì)象
 # 寫一行
 writer.writerow(['超哥哥',20])
 writer.writerow(['步驚云',22])
with open('test.csv','a') as f:
 writer = csv.writer(f)
 # 寫多行
 data_list = [('聶風(fēng)',23),('秦霜',30)]
 writer.writerows(data_list)

Windows中使用csv模塊默認(rèn)會(huì)在每行后面添加一個(gè)空行，使用newline=''可解決

with open('xxx.csv','w',newline='') as f:

貓眼電影top100抓取案例

確定URL網(wǎng)址

貓眼電影 - 榜單 - top100榜目標(biāo)

電影名稱、主演、上映時(shí)間操作步驟

1、查看是否為動(dòng)態(tài)加載

右鍵 - 查看網(wǎng)頁(yè)源代碼 - 搜索爬取關(guān)鍵字（查看在源代碼中是否存在）

2、找URL規(guī)律

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

3、正則表達(dá)式

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

4、編寫程序框架，完善程序

打印程序執(zhí)行時(shí)間
隨機(jī)的User-Agent,(確保每次發(fā)請(qǐng)求使用隨機(jī))
數(shù)據(jù)爬下來后做處理(字符串),定義成字典
一條龍: 獲取 -> 調(diào)用解析 -> 數(shù)據(jù)處理
貓眼電影數(shù)據(jù)存入本地 maoyanfilm.csv 文件

from urllib import request
import time
import re
import csv
import random
class MaoyanSpider(object):
 def __init__(self):
  self.page = 1 # 用于記錄頁(yè)數(shù)
  self.url = 'https://maoyan.com/board/4?offset={}'
  self.agent = [
   'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 \
   Safari/535.1',
   'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101 Firefox/6.0',
   'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; \
   .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; InfoPath.3)',
   'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1']

 # 請(qǐng)求
 def get_page(self, url):
  headers = {'User-Agent': random.choice(self.agent)} # 每次使用隨機(jī)的user-agent
  req = request.Request(url=url, headers=headers)  # 創(chuàng)建請(qǐng)求對(duì)象
  res = request.urlopen(req)       # 發(fā)起請(qǐng)求
  html = res.read().decode('utf-8')     # 獲取請(qǐng)求內(nèi)容
  self.parse_page(html)        # 直接調(diào)用解析函數(shù)

 # 解析
 def parse_page(self, html):
  pattren = re.compile(
   '<div class="movie-item-info">.*?title="(.*?)".*?class="star">(.*?)</p>.*?releasetime">(.*?)</p>', re.S)
  r_list = pattren.findall(html)
  # rlist: [('霸王別姬', '\n    主演：張國(guó)榮,張豐毅,鞏俐\n  ', '上映時(shí)間：1993-01-01'),(...),(...)]
  self.write_page(r_list)    # 寫入csv文件

 # # 保存,打印輸出
 # def write_page(self,r_list):
 #  one_film_dict = {}
 #  for rt in r_list:
 #   one_film_dict['name'] = rt[0].strip()
 #   one_film_dict['star'] = rt[1].strip()
 #   one_film_dict['time'] = rt[2].strip()[5:15]
 #
 #   print(one_film_dict)

 # 保存到csv文件(writerows) -- 推薦使用此方法
 def write_page(self, r_list):
  # 空列表,最終writerows()的參數(shù): [(),(),()]
  film_list = []
  with open('maoyan.csv', 'a',newline="") as f:
   writer = csv.writer(f)
   for rt in r_list:
    # 把處理過的數(shù)據(jù)定義成元組
    t = (rt[0], rt[1].strip(), rt[2].strip()[5:15])
    film_list.append(t)

   writer.writerows(film_list)
 def main(self):
  for offset in range(0, 31, 10):
   url = self.url.format(offset)
   self.get_page(url)
   time.sleep(random.randint(1, 3))
   print('第%d頁(yè)爬取完成' % self.page)
   self.page += 1
if __name__ == '__main__':
 start = time.time()
 spider = MaoyanSpider()
 spider.main()
 end = time.time()
 print('執(zhí)行時(shí)間: %.2f' % (end - start))

數(shù)據(jù)持久化存儲(chǔ)（MySQL數(shù)據(jù)庫(kù)）

讓我們來回顧一下pymysql模塊的基本使用

import pymysql

db = pymysql.connect('localhost', 'root', '123456', 'maoyandb', charset='utf8')
cursor = db.cursor() # 創(chuàng)建游標(biāo)對(duì)象
# execute()方法第二個(gè)參數(shù)為列表傳參補(bǔ)位
cursor.execute('insert into film values(%s,%s,%s)', ['霸王別姬', '張國(guó)榮', '1993'])
db.commit() # 提交到數(shù)據(jù)庫(kù)執(zhí)行
cursor.close() # 關(guān)閉
db.close()

讓我們來回顧一下pymysql中executemany()的用法

import pymysql

# 數(shù)據(jù)庫(kù)連接對(duì)象
db = pymysql.connect('localhost', 'root', '123456', charset='utf8')
cursor = db.cursor() # 游標(biāo)對(duì)象
ins_list = []   # 存放所有數(shù)據(jù)的大列表
for i in range(2):
 name = input('請(qǐng)輸入第%d個(gè)學(xué)生姓名:' % (i + 1))
 age = input('請(qǐng)輸入第%d個(gè)學(xué)生年齡:' % (i + 1))
 ins_list.append([name, age])

ins = 'insert into t3 values(%s,%s)' # 定義插入語(yǔ)句
cursor.executemany(ins, ins_list) # 一次數(shù)據(jù)庫(kù)的IO操作可插入多條語(yǔ)句，提升性能

db.commit()  # 提交到數(shù)據(jù)庫(kù)執(zhí)行
cursor.close() # 關(guān)閉游標(biāo)
db.close()  # 關(guān)閉數(shù)據(jù)庫(kù)

ins = 'insert into maoyanfilm values(%s,%s,%s)'
cursor.execute(['霸王', '國(guó)榮', '1991'])
cursor.executemany([
  ['月光寶盒', '周星馳', '1993'],
  ['大圣娶親', '周星馳', '1993']])

練習(xí)：把貓眼電影案例中電影信息存入MySQL數(shù)據(jù)庫(kù)中（盡量使用executemany方法）

from urllib import request
import time
import re
import pymysql
import random
class MaoyanSpider(object):
 def __init__(self):
  self.page = 1 # 用于記錄頁(yè)數(shù)
  self.url = 'https://maoyan.com/board/4?offset={}'
  self.ua_list = [
   'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) \
   Chrome/14.0.835.163 Safari/535.1',
   'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101 Firefox/6.0',
   'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; WOW64; Trident/4.0; SLCC2; \
   .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; InfoPath.3)']
  # 創(chuàng)建數(shù)據(jù)庫(kù)連接對(duì)象和游標(biāo)對(duì)象
  self.db = pymysql.connect('localhost', 'root', '123456', 'maoyandb', charset='utf8')
  self.cursor = self.db.cursor()
 # 獲取
 def get_page(self, url):
  # 每次使用隨機(jī)的user-agent
  headers = {'User-Agent': random.choice(self.ua_list)}
  req = request.Request(url=url, headers=headers)
  res = request.urlopen(req)
  html = res.read().decode('utf-8')
  self.parse_page(html)  # 直接調(diào)用解析函數(shù)

 # 解析
 def parse_page(self, html):
  pattren = re.compile(
   '<div class="movie-item-info">.*?title="(.*?)".*?class="star">(.*?)</p>.*?releasetime">(.*?)</p>', re.S)
  # rlist: [('霸王別姬','張國(guó)榮','1993'),(),()]
  r_list = pattren.findall(html)
  print(r_list)
  self.write_page(r_list)

 # 存入mysql數(shù)據(jù)庫(kù)(executemany([ [],[],[] ]))
 def write_page(self, r_list):
  film_list = []
  ins = 'insert into filmtab values(%s,%s,%s)'  # 定義插入語(yǔ)句
  # 處理數(shù)據(jù),放到大列表film_list中
  for rt in r_list:
   one_film = [rt[0], rt[1].strip(), rt[2].strip()[5:15]]
   # 添加到大列表中
   film_list.append(one_film)
  # 一次數(shù)據(jù)庫(kù)IO把1頁(yè)數(shù)據(jù)存入
  self.cursor.executemany(ins, film_list)
  # 提交到數(shù)據(jù)庫(kù)執(zhí)行
  self.db.commit()

 def main(self):
  for offset in range(0, 31, 10):
   url = self.url.format(offset)
   self.get_page(url)
   time.sleep(random.randint(1, 3))
   print('第%d頁(yè)爬取完成' % self.page)
   self.page += 1

  # 斷開數(shù)據(jù)庫(kù)(所有頁(yè)爬完之后)
  self.cursor.close()
  self.db.close()
if __name__ == '__main__':
 start = time.time()
 spider = MaoyanSpider()
 spider.main()
 end = time.time()
 print('執(zhí)行時(shí)間: %.2f' % (end - start))

讓我們來做個(gè)SQL命令查詢

1、查詢20年以前的電影的名字和上映時(shí)間

select name,time from filmtab where time<(now()-interval 20 year);

2、查詢1990-2000年的電影名字和上映時(shí)間

select name,time from filmtab where time>='1990-01-01' and time<='2000-12-31';

讓我們來復(fù)習(xí)一下mongdb數(shù)據(jù)庫(kù)

import pymongo
# 1.連接對(duì)象
conn = pymongo.MongoClient(host='127.0.0.1', port=27017)
db = conn['maoyandb']  # 2.庫(kù)對(duì)象
myset = db['filmtab']  # 3.集合對(duì)象
myset.insert_one({'name': '趙敏'}) # 4.插入數(shù)據(jù)庫(kù)

練習(xí)：把貓眼電影案例中電影信息存入MongDB數(shù)據(jù)庫(kù)中

from urllib import request
import re
import time
import random
import pymongo
class MaoyanSpider(object):
 def __init__(self):
  self.url = 'https://maoyan.com/board/4?offset={}'
  # 計(jì)數(shù)
  self.num = 0
  # 創(chuàng)建3個(gè)對(duì)象
  self.conn = pymongo.MongoClient('localhost', 27017)
  self.db = self.conn['maoyandb']
  self.myset = self.db['filmset']
  self.ua_list = [
   'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1',
   'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101 Firefox/6.0',
   'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET \
   CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; InfoPath.3)', ]

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

 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: [('霸王別姬','張國(guó)榮','1993'),()]
  film_list = pattern.findall(html)
  # 直接調(diào)用寫入函數(shù)
  self.write_html(film_list)
 # mongodb數(shù)據(jù)庫(kù)
 def write_html(self, film_list):
  for film in film_list:
   film_dict = {
    'name': film[0].strip(),
    'star': film[1].strip(),
    'time': film[2].strip()[5:15]
   }
   # 插入mongodb數(shù)據(jù)庫(kù)
   self.myset.insert_one(film_dict)
 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))
if __name__ == '__main__':
 start = time.time()
 spider = MaoyanSpider()
 spider.main()
 end = time.time()
 print('執(zhí)行時(shí)間:%.2f' % (end - start))

電影天堂案例（二級(jí)頁(yè)面抓?。?br />

1、查看是否為靜態(tài)頁(yè)面，是否為動(dòng)態(tài)加載

　　右鍵 - 查看網(wǎng)頁(yè)源代碼

2、確定URL地址

　　百度搜索：電影天堂 - 2019年新片 - 更多

3、目標(biāo)

*********一級(jí)頁(yè)面***********
1、電影名稱
2、電影鏈接
*********二級(jí)頁(yè)面***********

1、下載鏈接

4、步驟

找URL規(guī)律

第1頁(yè) ：https://www.dytt8.net/html/gndy/dyzz/list_23_1.html

第2頁(yè) ：https://www.dytt8.net/html/gndy/dyzz/list_23_2.html

第n頁(yè) ：https://www.dytt8.net/html/gndy/dyzz/list_23_n.html

寫正則表達(dá)式

1、一級(jí)頁(yè)面正則表達(dá)式（電影名稱、電影詳情鏈接）

2、二級(jí)頁(yè)面正則表達(dá)式

代碼實(shí)現(xiàn)

# decode('gbk','ignore') 注意ignore參數(shù)

# 注意結(jié)構(gòu)和代碼可讀性（一個(gè)函數(shù)不要太冗余）

from urllib import request
import re
import time
import random
from useragents import *
import pymysql
class FilmSky(object):
 def __init__(self):
  self.url = 'https://www.dytt8.net/html/gndy/dyzz/list_23_{}.html'
  # 定義兩個(gè)對(duì)象
  self.db = pymysql.connect('127.0.0.1', 'root', '123456', 'maoyandb', charset='utf8')
  self.cursor = self.db.cursor()

 # 獲取html函數(shù)(因?yàn)閮蓚€(gè)頁(yè)面都需要發(fā)請(qǐng)求)
 def get_page(self, url):
  req = request.Request(url=url, headers={'User-Agent': random.choice(ua_list)})
  res = request.urlopen(req)
  # ignore參數(shù),實(shí)在處理不了的編碼錯(cuò)誤忽略
  # 查看網(wǎng)頁(yè)源碼,發(fā)現(xiàn)網(wǎng)頁(yè)編碼為 gb2312,不是 utf-8
  html = res.read().decode('gbk', 'ignore')
  return html

 # 解析提取數(shù)據(jù)(把名稱和下載鏈接一次性拿到)
 # html為一級(jí)頁(yè)面響應(yīng)內(nèi)容
 def parse_page(self, html):
  # 1. 先解析一級(jí)頁(yè)面(電影名稱 和 詳情鏈接)
  pattern = re.compile('<table width="100%".*?<td height="26">.*?<a href="(.*?)" rel="external nofollow" rel="external nofollow" .*?>(.*?)</a>', re.S)
  # film_list: [('詳情鏈接','名稱'),()]
  film_list = pattern.findall(html)
  # [('/html/gndy/dyzz/20190806/58956.html', '019年驚悚動(dòng)作《報(bào)仇雪恨/血債血償》BD中英雙字幕'),(),()]
  ins = 'insert into filmsky values(%s,%s)'
  for film in film_list:
   film_name = film[1]
   film_link = 'https://www.dytt8.net' + film[0]
   # 2. 拿到詳情鏈接后,再去獲取詳情鏈接html,提取下載鏈接
   download_link = self.parse_two_html(film_link)

   self.cursor.execute(ins, [film_name, film_link])
   self.db.commit()

   # 打印測(cè)試
   d = {'電影名稱': film_name, '下載鏈接': download_link}
   print(d)

 # {'電影名稱': '019年驚悚動(dòng)作《報(bào)仇雪恨/血債血償》BD中英雙字幕', '下載鏈接': 'ftp://ygdy8:ygdy8@yg90.dydytt.net:8590/陽(yáng)光電影www.ygdy8.com.報(bào)仇雪恨.BD.720p.中英雙字幕.mkv'}
 # 解析二級(jí)頁(yè)面,獲取下載鏈接
 def parse_two_html(self, film_link):
  two_html = self.get_page(film_link)
  pattern = re.compile('<td style="WORD-WRAP.*?>.*?>(.*?)</a>', re.S)
  download_link = pattern.findall(two_html)[0]
  return download_link
 # 主函數(shù)
 def main(self):
  for page in range(1, 11):
   url = self.url.format(page)
   html = self.get_page(url)
   self.parse_page(html)
   time.sleep(random.randint(1, 3))
   print('第%d頁(yè)完成' % page)
if __name__ == '__main__':
 start = time.time()
 spider = FilmSky()
 spider.main()
 end = time.time()
 print('執(zhí)行時(shí)間:%.2f' % (end - start))

以上就是本文的全部?jī)?nèi)容，希望對(duì)大家的學(xué)習(xí)有所幫助，也希望大家多多支持腳本之家。

您可能感興趣的文章: