Scrapy基础01

一、Scarpy简介

Scrapy基于事件驱动网络框架 Twisted 编写。（Event-driven networking）

因此，Scrapy基于并发性考虑由非阻塞(即异步)的实现。

参考：武Sir笔记

参考：Scrapy 0.25 文档

参考：Scrapy架构概览

二、爬取chouti.com新闻示例

# chouti.py

# -*- coding: utf-8 -*-
import scrapy
from scrapy.http import Request
from scrapy.selector import HtmlXPathSelector
from ..items import Day24SpiderItem

# For windows:
import sys,io
sys.stdout=io.TextIOWrapper(sys.stdout.buffer,encoding='gb18030')

class ChoutiSpider(scrapy.Spider):
    name = 'chouti'
    allowed_domains = ['chouti.com']
    start_urls = ['http://chouti.com/']

    def parse(self, response):
        # print(response.body)
        # print(response.text)
        hxs = HtmlXPathSelector(response)
        item_list = hxs.xpath('//div[@id="content-list"]/div[@class="item"]')
        # 找到首页所有消息的连接、标题、作业信息然后yield给pipeline进行持久化
        for item in item_list:
            link = item.xpath('./div[@class="news-content"]/div[@class="part1"]/a/@href').extract_first()
            title = item.xpath('./div[@class="news-content"]/div[@class="part2"]/@share-title').extract_first()
            author = item.xpath('./div[@class="news-content"]/div[@class="part2"]/a[@class="user-a"]/b/text()').extract_first()
            yield Day24SpiderItem(link=link,title=title,author=author)

        # 找到第二页、第三页、、、第十页的消息，全部爬取下来做持久化
        # hxs.xpath('//div[@id="dig_lcpage"]//a/@href').extract()
        '''或者用正则精确匹配'''
        page_url_list = hxs.xpath('//div[@id="dig_lcpage"]//a[re:test(@href,"/all/hot/recent/\d+")]/@href').extract()
        for url in page_url_list:
            url = "http://dig.chouti.com" + url
            print(url)
            yield Request(url, callback=self.parse, dont_filter=False)

　　

# pipelines.py

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

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html

class Day24SpiderPipeline(object):

    def __init__(self,file_path):
        self.file_path = file_path  # 文件路径
        self.file_obj = None        # 文件对象：用于读写操作

    @classmethod
    def from_crawler(cls, crawler):
        """
        初始化时候，用于创建pipeline对象
        :param crawler:
        :return:
        """
        val = crawler.settings.get('STORAGE_CONFIG')
        return cls(val)

    def process_item(self, item, spider):
        print(">>>> ",item)
        if 'chouti' == spider.name:
            self.file_obj.write(item.get('link') + "\n" + item.get('title') + "\n" + item.get('author') + "\n\n")
        return item

    def open_spider(self, spider):
        """
        爬虫开始执行时，调用
        :param spider:
        :return:
        """
        if 'chouti' == spider.name:
            # 如果不加：encoding='utf-8' 会导致文件里中文乱码
            self.file_obj = open(self.file_path,mode='a+',encoding='utf-8')

    def close_spider(self, spider):
        """
        爬虫关闭时，被调用
        :param spider:
        :return:
        """
        if 'chouti' == spider.name:
            self.file_obj.close()

　　

# items.py

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

# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html

import scrapy

class Day24SpiderItem(scrapy.Item):
    link = scrapy.Field()
    title = scrapy.Field()
    author = scrapy.Field()

　　

# settings.py

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

# Scrapy settings for day24spider project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     http://doc.scrapy.org/en/latest/topics/settings.html
#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'day24spider'

SPIDER_MODULES = ['day24spider.spiders']
NEWSPIDER_MODULE = 'day24spider.spiders'

# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'day24spider (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = True

# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
#COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
#   'Accept-Language': 'en',
#}

# Enable or disable spider middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'day24spider.middlewares.Day24SpiderSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'day24spider.middlewares.MyCustomDownloaderMiddleware': 543,
#}

# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'day24spider.pipelines.Day24SpiderPipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

STORAGE_CONFIG = "chouti.json"
DEPTH_LIMIT = 1

　　

三、classmethod方法应用

from_crawler()   -->   __init__()