Scrapy 第一次爬虫（二）

写进文件中：

import scrapy


class SpellList(scrapy.Spider):
    name = "SpellList"
    start_urls = [
        "https://pvp.qq.com/web201605/summoner.shtml",
    ]
    def parse(self, response):
        spellList = response.css("#spellList li")
        spellList.css
        for spell in spellList:
            id = spell.css("li::attr(id)").extract_first()
            img = spell.css("img::attr(src)").extract_first()
            name = spell.css("p::text").extract_first()
            fileName = '技能.txt'  # 爬取的内容存入文件
            f = open(fileName, "a+")  # 追加写入文件
            f.write("id："+id )  # 写入ID内容
            f.write('\n')  # 换行
            f.write("name："+name)  # 写入技能名字内容
            f.write('\n')  # 换行
            f.write("img：https:"+ img)  # 写入图片链接内容
            f.write('\n')  # 换行
            f.close()  # 关闭文件操作

Oh 上面执行完后，打开后有乱码将

f = open(fileName, "a+")  # 追加写入文件

后改为：

f = open(fileName, "a+", encoding="utf-8")  # 追加写入文件

用xpath实现：

        spell_list = response.xpath("//ul[@id='spellList']/ancestor::*")
        logging.info(spell_list)
        for spell in spell_list:
            id = spell.xpath("//li//@id").extract_first()
            logging.info("id :" + id)
            img = spell.xpath("//img//@src").extract_first()
            logging.info("img :" + img)
            name = spell.xpath("//p//text()").extract_first()
            logging.info("name :" + name)