Scrapy---在线爬取网页数据
1、items.py
class DoubanItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
# 电影排名
rank = scrapy.Field()
# 电影标题
title = scrapy.Field()
picUrl = scrapy.Field()
pass2、shoubanspider.py
# -*- coding: utf-8 -*-
import scrapy
# from 工程名称.文件名 import 类名
from douban.items import DoubanItem
import sys
# 设置中文格式
utf8 = "utf-8"
if sys.getdefaultencoding() != utf8:
reload(sys)
sys.setdefaultencoding(utf8)
pass
class DoubanspiderSpider(scrapy.Spider):
name = 'doubanspider'
allowed_domains = ['https://~~~~~~~要爬取的网页网址~~~~~~~~~']
start_urls = ['https://~~~~~~~要爬取的网页网址~~~~~~~~~']
def parse(self, response):
# 找到爬取的数据，进行解析，获取到多条数据，
items=response.xpath("//div[@class='item']")
# 获取每一条数据,进行循环
for item in items:
doubanItem=DoubanItem()
doubanItem['rank']=item.xpath('div[@class="pic"]/em/text()').extract()
doubanItem['title']=item.xpath('div[@class="info"]/div[@class="hd"]/a/span[@class="title"]/text()').extract()
doubanItem['picUrl']=item.xpath('div[@class="pic"]/a/img/@src').extract()
yield doubanItem
pass
3、pipelines.py（数据处理）
（1）输出pipelines.py
class DoubanPipeline(object):
def process_item(self, item, spider):
print(item['rank'][0])
print(item['title'][0])
return item
（2）保存为txt格式pipelinestxt.py
import sys
# 配置中文环境
utf8='utf-8'
if sys.getdefaultencoding() != utf8:
reload(sys)
sys.setdefaultencoding(utf8)
pass
import os
import time
class DoubanPipeline(object):
# 定义构造函数
def __init__(self):
# 定义文件夹名
self.folder_name="output"
# 判断文件夹是否存在，不存在时创建文件夹
if not os.path.exists(self.folder_name):
os.mkdir(self.folder_name)
def process_item(self, item, spider):
print("———————————进行数据保存保存格式为txt————————")
# 获取当前日期
current_time=time.strftime('%Y_%m_%d',time.localtime())
# 创建文件
file_name='douban'+current_time+'.txt'
try:
with open(self.folder_name+'/'+file_name,'a',encoding='utf-8') as fp:
fp.write('标题：'+item['rank'][0]+'\n')
fp.write('内容：'+item['title'][0]+'\n\n')
except IOError as err:
print('error:'+str(err))
finally:
fp.close()
return item
（3）保存为json格式pipelinesJson.py
import os
import time
import codecs
import json
class DoubanPipeline(object):
# 定义构造函数
def __init__(self):
# 定义文件夹名
self.folder_name="output"
# 判断文件夹是否存在，如果不存在时创建文件夹
if not os.path.exists(self.folder_name):
os.mkdir(self.folder_name)
def process_item(self, item, spider):
print("———————————进行数据保存保存格式为json————————")
# 获取当前时间
current_data=time.strftime('%Y_%m_%d',time.localtime())
file_name='moielist'+current_data+'.json'
try:
with codecs.open(self.folder_name+'/'+file_name,'a',encoding='utf-8') as fp:
listDic=json.dumps(dict(item),ensure_ascii=False)+'\n'
fp.write(listDic)
except IOError as err:
print('error:'+str(err))
finally:
fp.close()
return item（4）保存为xls格式
import os
import time
# 创建工作簿、创建sheet
import xlwt
# 打开
import xlrd
from xlutils.copy import copy
class DoubanPipeline(object):
# 定义构造函数
def __init__(self):
# 定义文件夹名
folder_name="output"
# 判断文件夹是否存在，如果不存在时创建文件夹
if not os.path.exists(folder_name):
os.mkdir(folder_name)
# 创建文件
current_time=time.strftime('%Y-%m-%d',time.localtime())
file_name='douban'+current_time+'.xls'
self.excel_path=folder_name+'/'+file_name
# 创建excel文件
self.workbook=xlwt.Workbook(encoding='utf-8')
# 创建excel下面的sheel
self.doubansheet=self.workbook.add_sheet(u'电影数据')
headers=[u'排名',u'标题']
for i in range(len(headers)):
self.doubansheet.write(0,i,headers[i])
self.workbook.save(self.excel_path)
self.index=1
def process_item(self, item, spider):
print("———————————进行数据保存保存格式为xls————————")
# 打开工作簿
oldwd=xlrd.open_workbook(self.excel_path,formatting_info=True)
newWd=copy(oldwd)
sheet=newWd.get_sheet(0)
list1=[item['rank'],item['title']]
for i in range(len(list1)):
sheet.write(self.index,i,list1[i])
# 保存
newWd.save(self.excel_path)
self.index=self.index+1
return item
（5）保存图片
import os
import urllib.request
class DoubanPipeline(object):
# 定义构造函数
def __init__(self):
# 定义文件夹名
self.folder_name="images"
# 判断文件夹是否存在，如果不存在时创建文件夹
if not os.path.exists(self.folder_name):
os.mkdir(self.folder_name)
def process_item(self, item, spider):
print("———————————保存图片————————")
pic_url=item['picUrl'][0]
image_name=pic_url.split('/')[-1]
try:
urllib.request.urlretrieve(pic_url,self.folder_name+"/%s" %image_name)
except Exception as err:
print('error:'+str(err))
return item（6）保存为数据库格式
import pymysql
class DoubanPipeline(object):
def process_item(self, item, spider):
print("———————————将数据保存到MySQL中————————")
try:
con=pymysql.connect(host='localhost',user='root',passwd='1',db='douban',port=3306,charset='utf8')
if con:
print('————————链接成功———————')
# 获取游标
cur=con.cursor()
if cur:
print('————————游标获取成功———————')
rank=item['rank'][0]
title=item['title'][0]
# sql添加语句
sql='insert into doubaninfo values(null,%s,%s)'
cur.execute(sql,(rank,title))
con.commit()
cur.close()
else:
print('————————游标获取失败———————')
else:
print('————————链接失败———————')
finally:
con.close()
return item4、配置settings文件
请求头
DOWNLOADER_MIDDLEWARES = {
'douban.middlewares.DoubanDownloaderMiddleware': 543,
'scrapy.contrib.downloadermiddleware.useragent.UserAgentMiddleware' : None,
'douban.rotate_useragent.RotateUserAgentMiddleware' :400
}执行顺序
ITEM_PIPELINES = {
'douban.pipelines.DoubanPipeline': 300,
'douban.pipelinestxt.DoubanPipeline': 301,
'douban.pipelinesjson.DoubanPipeline': 302,
'douban.pipelinesexcel.DoubanPipeline': 303,
'douban.pipelinesmysql.DoubanPipeline': 304,
'douban.pipelinespic.DoubanPipeline': 305,
}