爬取100页京东商品评论

#items.py
import scrapy
class InsistItem(scrapy.Item):
    comment=scrapy.Field()

#pipelines.py
import json
class InsistPipeline(object):
    def __init__(self):
        self.f=open('tencent.json','w',encoding='gbk')
    def process_item(self, item, spider):
        #item(Item对象，被爬取的item)
        #这个方
        content=json.dumps(dict(item),ensure_ascii=False)+",\n"
        self.f.write(content)
        return item

#tengxun.py
import scrapy
from insist.items import InsistItem
import json

class TengxunSpider(scrapy.Spider):
    name = 'tengxun'
    allowed_domains = ['sclub.jd.com']
    #start_urls = ['https://item.jd.com/4432058.html']
    baseURL = 'https://sclub.jd.com/comment/productPageComments.action?productId=4432058&score=0&sortType=5&pageSize=10&isShadowSku=0&rid=0&fold=1&page='
    offset = 0
    start_urls = [baseURL + str(offset)]
    def parse(self, response):
       com=json.loads(response.body.decode('gbk'))
       comment=com['comments']
       for co in comment:
           item = InsistItem()
           item['comment']=co['content']
           yield item
       if self.offset<100:
           self.offset+=1
           yield  scrapy.Request(self.baseURL+str(self.offset),callback=self.parse)

 

转载于:https://www.cnblogs.com/persistence-ok/p/11576574.html