爬取微信小程序

-- coding: utf-8 --

import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule

class WxSpider(CrawlSpider):
name = ‘wx’
allowed_domains = [‘wxapp-union.com’]
start_urls = [‘http://www.wxapp-union.com/portal.php?mod=list&catid=1&page=1’]

rules = (
    #列表页
    Rule(LinkExtractor(allow=r'http://www.wxapp-union.com/portal.php\?mod=list&catid=1&page=\d+'), follow=True),
    #详情页
    Rule(LinkExtractor(allow=r'http://www.wxapp-union.com/article-\d+-1.html'), callback='parse_item')
)

def parse_item(self, response):
    item = {}
    #item['domain_id'] = response.xpath('//input[@id="sid"]/@value').get()
    #item['name'] = response.xpath('//div[@id="name"]').get()
    #item['description'] = response.xpath('//div[@id="description"]').get()
    item['title']=response.xpath('//*[@id="ct"]/div[1]/div/div[1]/div/div[2]/div[1]/h1/text()').extract_first()
    item['author']=response.xpath('//*[@id="ct"]/div[1]/div/div[1]/div/div[2]/div[3]/div[1]/p/a/text()').extract_first()
    item['time']=response.xpath('//*[@id="ct"]/div[1]/div/div[1]/div/div[2]/div[3]/div[1]/p/span/text()').extract_first()
    return item