Scrapy项目(东莞阳光网)---利用Spider爬取贴子内容,包含图片(使用Pycharm)

1、创建Scrapy项目

scapy startproject dongguan2

2.进入项目目录,使用命令genspider创建Spider

scrapy genspider xixi "wz.sun0769.com"

3、定义要抓取的数据(处理items.py文件)

# -*- coding: utf-8 -*-
import scrapy

class Dongguan2Item(scrapy.Item):
    # 贴子编号
    number = scrapy.Field()
    # 贴子标题
    title = scrapy.Field()
    # 贴子内容
    content = scrapy.Field()
    # 贴子url
    url = scrapy.Field()
    # 有图贴子的链接地址
    image_link = scrapy.Field()

4、编写提取item数据的Spider(在spiders文件夹下:xixi.py)

# -*- coding: utf-8 -*-
import scrapy
import re
# 如果下面在pycharm中有红色波浪线,参照这个设置:https://blog.csdn.net/z564359805/article/details/80650843
from dongguan2.items import Dongguan2Item

class XixiSpider(scrapy.Spider):
    name = 'xixi'
    allowed_domains = ['wz.sun0769.com']
    url = "http://wz.sun0769.com/index.php/question/report?page="
    offset = 0
    start_urls = [url + str(offset)]
    def parse(self, response):
        # 获取贴子的链接地址列表
        links = response.xpath('//a[@class="news14"]/@href').extract()
        for link in links:
            yield scrapy.Request(link,callback=self.parse_item)
        # 获取到最后一页的链接,记得是列表要加[0]
        end_link = response.xpath('//div[@class="pagination"]/a[last()]/@href').extract()[0]
        # 利用正则取出最后的数字也就是offset的最大值
        offset_max = re.search(r'page=(\d+)', end_link).group(1)
        if self.offset <= int(offset_max):
            self.offset += 30
            yield scrapy.Request(self.url + str(self.offset),callback=self.parse)
    def parse_item(self,response):
        item = Dongguan2Item()
        # 每个贴子中的标题,strip()去除首尾空格
        item['title'] = response.xpath('//div[@class="pagecenter p3"]//strong/text()').extract()[0].strip()
        # 根据标题提取出编号
        item['number'] = item['title'].split(":")[-1].strip()
        # 先取出贴子内容有图的情况
        content = response.xpath('//div[@class="contentext"]/text()').extract()
        if len(content) == 0:
            # 代表没有图
            content = response.xpath('//div[@class="c1 text14_2"]/text()').extract()
            # content为列表,通过join方法拼接为字符串,并去除首尾空格,以及将内容中的空格去掉
            item['content'] = "".join(content).strip().replace("\xa0", "")
            # 如果贴子没有图要给item['image_link']赋默认值,否则写入的时候会报NoneType错
            item['image_link'] = "此贴无图"
        else:
            # 贴子有图情况,将图的链接地址取出来放在item['image_link']
            item['image_link'] = response.xpath('//div[@class="textpic"]/img/@src').extract()[0]
            # content为列表,通过join方法拼接为字符串,并去除首尾空格,以及将内容中的空格去掉
            item['content'] = "".join(content).strip().replace("\xa0", "")
        # 贴子的链接地址
        item['url'] = response.url
        yield item

5.处理pipelines管道文件保存数据,可将结果保存到文件中(pipelines.py)

# -*- coding: utf-8 -*-
import scrapy
import json
import os,os.path
from scrapy.utils.project import get_project_settings
from scrapy.pipelines.images import ImagesPipeline

# 继承ImagesPipeline()的子类处理图片并保存,参考:https://blog.csdn.net/z564359805/article/details/80693578
class ImagePipeline(ImagesPipeline):
    # 获取settings文件中设置的图片保存地址IMAGES_STORE
    IMAGES_STORE =get_project_settings().get("IMAGES_STORE")
    def get_media_requests(self, item, info):
        # 如果贴子有图,处理贴子图片地址
        if item['image_link'] != '此贴无图':
            image_url = item['image_link']
            full_image_url = "http://wz.sun0769.com"+str(image_url)
            yield scrapy.Request(full_image_url)
    def item_completed(self, results, item, info):
        if item['image_link'] != '此贴无图':
            image_url = item['image_link']
            # 拼接成图片链接地址并打印提示
            full_image_url = "http://wz.sun0769.com" + str(image_url)
            print('\n' + "此贴子有图片,链接地址为:%s" % full_image_url)
            image_path = [x['path'] for ok, x in results if ok]
            os.rename(self.IMAGES_STORE + '/' + image_path[0],self.IMAGES_STORE + '/' + item['number'] + '.jpg')
            # 如果贴子有图,修改item['image_link']为本地图片地址,这里不修改注释掉了
            # item['image_link'] = self.IMAGES_STORE + '/' + item['number']
        return item

# 转码操作,继承json.JSONEncoder的子类,在json目录下的encoder.py中
class MyEncoder(json.JSONEncoder):
    def default(self, o):
        if isinstance(o,bytes):
            return str(o,encoding='utf-8')
        return JSONEncoder.default(self, o)
class Dongguan2Pipeline(object):
    def __init__(self):
        self.file = open("dongguan.json",'w',encoding='utf-8')
    def process_item(self, item, spider):
        text = json.dumps(dict(item),ensure_ascii=False,cls=MyEncoder)+ '\n'
        self.file.write(text)
        return item
    def close_spider(self,spider):
        print("数据处理完毕,谢谢使用!")
        self.file.close()

6.配置settings文件(settings.py)

# Obey robots.txt rules,具体含义参照:https://blog.csdn.net/z564359805/article/details/80691677  
ROBOTSTXT_OBEY = False    
# Override the default request headers:添加User-Agent信息  
DEFAULT_REQUEST_HEADERS = {  
  'User-Agent': 'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0);',  
  # 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',  
  # 'Accept-Language': 'en',  
}  
# 图片保存地址,这样会在当前执行的目录下创建images文件夹,也可以写具体地址
IMAGES_STORE = "./images"
# Configure item pipelines
ITEM_PIPELINES = {
   'dongguan2.pipelines.Dongguan2Pipeline': 300,
   'dongguan2.pipelines.ImagePipeline': 3,
}
# 还可以将日志存到本地文件中(可选添加设置)
LOG_FILE = "dongguanlog.log"
LOG_LEVEL = "DEBUG"

7.以上设置完毕,进行爬取:执行项目命令crawl,启动Spider:

scrapy crawl xixi

猜你喜欢

转载自blog.csdn.net/z564359805/article/details/80693034