抓取微信里面小程序里的文字信息--yuke

import scrapy
import json

class QiubaiSpider(scrapy.Spider):
    name = 'qiubai'
    start_urls = ['https://mp.weixin.qq.com/s/n7E2PCcXppbLMXtR_Um-FA']

    def parse(self, response):
        div_list = response.xpath(
            '//*[@id="js_content"]/section[2]/section[1]/section/section[2]/section/p')

        id_list = []
        for div in div_list:
            div_list2 = div.xpath('./span[1]/text()').extract_first()
            if div_list2 != None:
                print(div_list2)
                id_list.append(div_list2)
                fp = open('./语文重点.txt', 'w', encoding='utf-8')
                json.dump(id_list, fp, ensure_ascii=False)

scrapy crawl qiubai