python_scrapy_爬虫

import scrapy
from scrapy.spiders import Rule
from scrapy.linkextractors import LinkExtractor
from ..items import BookBQGItem


class KaoshiBqgSpider(scrapy.Spider):
    name = ‘kaoshi_bqg‘
    allowed_domains = [‘biquge5200.cc‘]
    start_urls = [‘https://www.biquge5200.cc/xuanhuanxiaoshuo/‘]

    rules = (
        # 编写匹配文章列表的规则
        Rule(LinkExtractor(allow=r‘https://www.biquge5200.cc/xuanhuanxiaoshuo/‘), follow=True),
        # 匹配文章详情
        Rule(LinkExtractor(allow=r‘.+/[0-9]{1-3}_[0-9]{2-6}/‘), callback=‘parse_item‘, follow=False),
    )

    # 小书书名
    def parse(self, response):
        a_list = response.xpath(‘//*[@id="newscontent"]/div[1]/ul//li//span[1]/a‘)
        for li in a_list:
            name = li.xpath(".//text()").get()
            detail_url = li.xpath(".//@href").get()
            yield scrapy.Request(url=detail_url, callback=self.parse_book, meta={‘info‘: name})

    #  单本书所有的章节名
    def parse_book(self, response):
        name = response.meta.get(‘info‘)
        list_a = response.xpath(‘//*[@id="list"]/dl/dd[position()>20]//a‘)
        for li in list_a:
            chapter = li.xpath(".//text()").get()
            url = li.xpath(".//@href").get()
            yield scrapy.Request(url=url, callback=self.parse_content, meta={‘info‘: (name, chapter)})

    # 每章节内容
    def parse_content(self, response):
        name, chapter = response.meta.get(‘info‘)
        content = response.xpath(‘//*[@id="content"]//p/text()‘).getall()
        item = BookBQGItem(name=name, chapter=chapter, content=content)
        yield item

import scrapy


# 笔趣阁字段
class BookBQGItem(scrapy.Item):
    name = scrapy.Field()
    chapter = scrapy.Field()
    content = scrapy.Field()


# 喜马拉雅 字段
class BookXMLYItem(scrapy.Item):
    book_name = scrapy.Field()
    book_id = scrapy.Field()
    book_url = scrapy.Field()
    book_author = scrapy.Field()


# 喜马拉雅详情字段
class BookChapterItem(scrapy.Item):
    book_id = scrapy.Field()
    chapter_id = scrapy.Field()
    chapter_name = scrapy.Field()
    chapter_url = scrapy.Field()

from scrapy.exporters import JsonLinesItemExporter


class BqgPipeline(object):
    def __init__(self):
        self.fp = open("biquge.json", ‘wb‘)
        #  JsonLinesItemExporter 调度器
        self.exporter = JsonLinesItemExporter(self.fp, ensure_ascii=False)

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

    def close_item(self):
        self.fp.close()
        print("爬虫结束")


# class XmlyPipeline(object):
#     def __init__(self):
#         self.fp = open("xmly.json", ‘wb‘)
#         #  JsonLinesItemExporter 调度器
#         self.exporter = JsonLinesItemExporter(self.fp, ensure_ascii=False)
#
#     def process_item(self, item, spider):
#         self.exporter.export_item(item)
#         return item
#
#     def close_item(self):
#         self.fp.close()
#         print("爬虫结束")

from scrapy import cmdline

cmdline.execute("scrapy crawl kaoshi_bqg".split())
# cmdline.execute("scrapy crawl xmly".split())