21天打造分布式爬虫-Crawl类爬取小程序社区（八） - zhang_derek

21天打造分布式爬虫-Crawl类爬取小程序社区（八）

8.1.Crawl的用法实战

新建项目

scrapy startproject wxapp

scrapy genspider -t crawl wxapp_spider "wxapp-union.com"

wxapp_spider.py

# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from wxapp.items import WxappItem

class WxappSpiderSpider(CrawlSpider):
    name = \'wxapp_spider\'
    allowed_domains = [\'wxapp-union.com\']
    start_urls = [\'http://www.wxapp-union.com/portal.php?mod=list&catid=2&page=1\']

    rules = (
        Rule(LinkExtractor(allow=r\'.+mod=list&catid=\d\'), follow=True),
        Rule(LinkExtractor(allow=r\'.+article-.+\.html\'), callback="parse_detail",follow=False),
    )

    def parse_detail(self, response):
        title = response.xpath("//h1[@class=\'ph\']/text()").get()
        author_p = response.xpath("//p[@class=\'authors\']")
        author = author_p.xpath(".//a/text()").get()
        pub_time = author_p.xpath(".//span/text()").get()
        article_content = response.xpath("//td[@id=\'article_content\']//text()").getall()
        content = "".join(article_content).strip()
        item = WxappItem(title=title,author=author,pub_time=pub_time,content=content)
        return item

items.py

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


import scrapy

class WxappItem(scrapy.Item):
    title = scrapy.Field()
    author = scrapy.Field()
    pub_time = scrapy.Field()
    content = scrapy.Field()

pipelines.py

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

from scrapy.exporters import JsonLinesItemExporter

class WxappPipeline(object):
    def __init__(self):
        self.fp = open(\'wxapp.json\',\'wb\')
        self.exporter = JsonLinesItemExporter(self.fp, ensure_ascii=False, encoding=\'utf-8\')

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

    def close_spider(self, spider):
        self.fp.close()

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 = {
   \'wxapp.pipelines.WxappPipeline\': 300,
}

 

start.py

from scrapy import cmdline

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