利用scrapy框架爬取糗事百科

qsbk.py 代码

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


class QsbkSpider(scrapy.Spider):
    name = 'qsbk'
    allowed_domains = ['qiushibaike.com']
    start_urls = ['https://www.qiushibaike.com/text/page/1/']
    def parse(self, response):
        for i in range(2,10):
            next_url = 'https://www.qiushibaike.com/text/page/{}/'.format(i)
            yield scrapy.Request(next_url, callback=self.parse_xq)




    def parse_xq(self, response):
        # with open('qsbk.html','wb') as f:
        #     f.write(response.body)
        item = QsbkItem()
        contents = response.xpath('//div[@class="content"]/span/text()').extract()

        print(contents)
        numbers = response.xpath('//span[@class="stats-vote"]/i/text()').extract()
        print(numbers)
        comments = response.xpath('//div[@class="stats"]/span[2]/a/i/text()').extract()
        print(comments)
        for i in range(0,len(numbers)):
            content = ''.join(contents[i])
            item['content'] = content
            item['number'] = numbers[i] + '好笑'
            item['comment'] = comments[i] + '评论'
            yield item

items.py 文件代码

class QsbkItem(scrapy.Item):
    content = scrapy.Field()
    number = scrapy.Field()
    comment = scrapy.Field()
    def get_insert_sql(self):
        sql = 'insert into qsbk_test(content,number,comment)values (%s,%s,%s)'
        data = (self['content'],self['number'],self['comment'])
        return (sql,data)

pipelines.py文件代码

class MysqlProjectPipeline(object):
    def process_item(self, item, spider):
        (insert_sql,data) = item.get_insert_sql()
        myhelper = MysqlHelper()
        myhelper.execute_modify_sql(insert_sql,data)

其他配置见文件scrapy基本框架位置