21天打造分布式爬虫-Scrapy框架（七）

7.1.糗事百科

安装

pip install pypiwin32

pip install 

pip install scrapy

创建和运行项目

scrapy startproject qsbk   #创建项目

scrapy genspider qsbk_spider "qiushibaike.com"   #创建爬虫

scrapy crawl qsbk_spider         #运行爬虫

代码

qsbk_spider.py

# -*- coding: utf-8 -*-
import scrapy
from qsbk.items import QsbkItem

class QsbkSpiderSpider(scrapy.Spider):
    name = 'qsbk_spider'
    allowed_domains = ['qiushibaike.com']
    start_urls = ['https://www.qiushibaike.com/8hr/page/1/']
    base_domain = "https://www.qiushibaike.com"

    def parse(self, response):
        duanzidivs = response.xpath("//div[@id='content-left']/div")
        for duanzidiv in duanzidivs:
            author = duanzidiv.xpath(".//h2/text()").get().strip()
            content = duanzidiv.xpath(".//div[@class='content']//text()").getall()
            content = "".join(content).strip()
            item = QsbkItem(author=author,content=content)
            yield item
        #爬后面页的数据
        next_url = response.xpath("//ul[@class='pagination']/li[last()]/a/@href").get()
        if not next_url:
            return
        else:
            yield scrapy.Request(self.base_domain+next_url,callback=self.parse)

item.py

import scrapy

class QsbkItem(scrapy.Item):
    author = scrapy.Field()
    content = scrapy.Field()

pipelines.py

# -*- coding: utf-8 -*-

import json

#1.手动把dick转换成json格式

# class QsbkPipeline(object):
#     def __init__(self):
#         self.fp = open('duanzi.json','w',encoding='utf-8')
#
#     def open_spider(self,spider):
#         print('开始爬虫')
#
#     def process_item(self, item, spider):
#         item_json = json.dumps(dict(item),ensure_ascii=False)
#         self.fp.write(item_json+'\n')
#         return item
#
#     def close_spider(self,spider):
#         self.fp.close()
#         print('爬虫结束了')

#2.适用JsonItemExporter，使用与数据量小的情况下
# from scrapy.exporters import JsonItemExporter
# class QsbkPipeline(object):
#     def __init__(self):
#         self.fp = open('duanzi.json','wb')
#         self.exporter = JsonItemExporter(self.fp,ensure_ascii=False,encoding='utf-8')
#         self.exporter.start_exporting()
#
#     def open_spider(self,spider):
#         print('开始爬虫')
#
#     def process_item(self, item, spider):
#         self.exporter.export_item(item)
#         return item
#
#     def close_spider(self,spider):
#         self.exporter.finish_exporting()
#         self.fp.close()
#         print('爬虫结束了')


#3.JsonLinesItemExporter，适用与数据量大的情况下
from scrapy.exporters import JsonLinesItemExporter
class QsbkPipeline(object):
    def __init__(self):
        self.fp = open('duanzi.json','wb')
        self.exporter = JsonLinesItemExporter(self.fp,ensure_ascii=False,encoding='utf-8')

    def open_spider(self,spider):
        print('开始爬虫')

    def process_item(self, item, spider):
        self.exporter.export_item(item)
        return item

    def close_spider(self,spider):
        self.fp.close()
        print('爬虫结束了')

settings.py

ROBOTSTXT_OBEY = False

DOWNLOAD_DELAY = 1

DEFAULT_REQUEST_HEADERS = {
  'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
  # 'Accept-Language': 'en',
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36',
}

ITEM_PIPELINES = {
   'qsbk.pipelines.QsbkPipeline': 300,
}

start.py

from scrapy import cmdline

cmdline.execute("scrapy crawl qsbk_spider".split())