聲明：
1、本博客所涉及爬蟲及其爬取的數(shù)據(jù)僅用于爬蟲技術(shù)研究，請(qǐng)勿用于商業(yè)用途梯轻。
2褪迟、本博文中涉及的網(wǎng)址均已隱去關(guān)鍵字段冗恨。

基于python3.5版本

源代碼

spidertest.py

# -*- coding: utf-8 -*-
import scrapy
from testscrapy01.items import QIBEBT_Zhuanli_Item
from scrapy.selector import Selector
import re

class QibebtZhuanliSpider(scrapy.Spider):

    name = "xxxx_zhuanli_01"
    allowed_domains = ["qibebt.cas.cn"]
    start_urls = ['http://www.xxxx.cas.cn/kycg/zl/index.html']

    lst = []
    for i in range(1,15):
        start_urls.append("http://www.xxxx.cas.cn/kycg/zl/index_" + str(i) +".html")

    # start_urls = ['http://www.xxxx.cas.cn/kycg/zl/index.html'] + lst

    def parse(self, response):
        print("目標(biāo)網(wǎng)頁(yè)為：" + response.url)
        hxs = Selector(response)
        qitem = QIBEBT_Zhuanli_Item()
        # 把所有行抓取出來(lái)
        zls = hxs.xpath("http://tr[@bgcolor='#f2f7f1']")
        # print(len(zls))
        for zl in zls:
            #專利名稱
            name = zl.xpath("td[@height='26']/a[@target='_blank']/text()").extract()[0]
            # name = zl.xpath("http://a/text()").extract()

            #專利類別
            type = zl.xpath("td[@align='center']/text()").extract()[0]

            #申請(qǐng)?zhí)?            number = zl.xpath("td[@align='center']/text()").extract()[1]
            #申請(qǐng)日期
            apply_date = zl.xpath("td[@align='center']/text()").extract()[2]
            sq_date = "無(wú)"
            try:
                #授權(quán)日期
                sq_date = zl.xpath("td[@align='center']/text()").extract()[3]
            except:
                sq_date = "無(wú)"
            #發(fā)明人
            #有一個(gè)"\xa0"字符串，進(jìn)行特殊處理
            inventor = repr(zl.xpath("td[@align='left']/text()").extract()[0])
            # print(isinstance(inventor,str))
            inventor = re.sub(r"'","",inventor)
            # inventor = re.sub("\\xa0", ",", inventor)
            main_inventor = inventor.split('\\xa0')[0]
            other_inventors = inventor.split('\\xa0')[1]

            # print("專利名稱 = ", name)
            # print("專利類別 = ", type)
            # print("申請(qǐng)?zhí)?= ", number)
            # print("申請(qǐng)日期 = ", apply_date)
            # print("授權(quán)日期 = ", sq_date)
            # print("第一發(fā)明人 = ", main_inventor)
            # print("其他發(fā)明人 = ", other_inventors)
            # print("")
            yield qitem