今天爬取中彩網福彩3d[http://www.zhcw.com/3d/]的時候，碰到iframe巢狀，xpath始終取不到值，如下圖： 無論怎麼取值，都為null，後來發現有個這個東西 然後直接進入到url裡面，就可以取到值了 好了，問題解決，查閱網上資料，聽說可以正面攻克，比較麻煩，不推薦花時間去做這東西。 最後附上本人程式碼,爬蟲框架用的是scrapy，儲存用的MySQL資料庫。 items

import scrapy


class Lottery3DItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
 

    # 開獎日期
    date = scrapy.Field()
    # 期號
    issue = scrapy.Field()
    # 第一個藍球號碼
    blue1 = scrapy.Field()
    # 第二個藍球號碼
    blue2 = scrapy.Field()
    # 第三個藍球號碼
    blue3 = scrapy.Field()

spider

# -*- coding: utf-8 -*-
import scrapy
from ..items import Lottery3DItem


class LotterySpider(scrapy.
 
Spider):
    name = 'lottery'
    allowed_domains = ['zhcw.com']
    start_urls = ['http://kaijiang.zhcw.com/zhcw/html/3d/list_1.html']
    index = 1
    items = []

    def parse(self, response):
        node_list = response.xpath("//tr")
        node_list.pop(0)
        node_list.pop(0)
        node_list.pop(
 
)
        for node in node_list:
            item = Lottery3DItem()

            item["date"] = node.xpath("./td[1]/text()").extract_first()
            item["issue"] = node.xpath("./td[2]/text()").extract_first()
            item["blue1"] = node.xpath("./td[3]/em[1]/text()").extract_first()
            item["blue2"] = node.xpath("./td[3]/em[2]/text()").extract_first()
            item["blue3"] = node.xpath("./td[3]/em[3]/text()").extract_first()

            yield item

        self.index += 1
        next_url = "http://kaijiang.zhcw.com/zhcw/html/3d/list_{}.html".format(self.index)
        yield scrapy.Request(url=next_url, callback=self.parse)

pipeline

import pymysql


class Lottery3DPipeline(object):

 def __init__(self):
     self.conn = pymysql.connect(host='103.27.5.156', user='developer', passwd='Developer!123', db='spider', charset='utf8')
     self.cursor = self.conn.cursor()

 def process_item(self, item, spider):
     lottery_date = item['date']
     issue = item['issue']
     blue1 = item['blue1']
     blue2 = item['blue2']
     blue3 = item['blue3']
     sql = "insert into lottery_3d(date, issue, blue1, blue2, blue3) VALUES(%s, %s, %s, %s, %s)"
     self.cursor.execute(sql, (lottery_date, issue, blue1, blue2, blue3,))
     self.conn.commit()
     return item

 def close_spider(self, spider):
     self.conn.close()