爬虫札记

/html/body/div[4]/div/div/div[2]/div[3]/div[2]


/html/body/div[4]/div/div/div[2]/div[3]/div[2]/ul/li[1]/a/span

doc_list list-6791341
sel.xpath('//ul[@class="doc_list"]/li/a//span/text()').extract()[0]

${resp.selector('.doc_list').selector('.odd').attr('data-tweet-id')}

${resp.xpaths('//ul[@class="doc_list"]/li/a//span/text()').extract()[0]}

${extract.selectors(resp.html,'.categorical-project-card a','attr','href')}

#color_printsssss > div.j-fontContent.newscontnet.minh500 > table > tbody > tr:nth-child(1) > td:nth-child(2)

${extract.selectors(resp.html,'#color_printsssss > div.j-fontContent.newscontnet.minh500 > table > tbody > tr:nth-child(1) > td:nth-child(2)','text')}

#page_6791341 > span.total

#page_6791341

//*[@class="pagination"]/span[3]

//*[@class="pagination"]/a[8]

${resp.xpaths('//*[@class="pagination"]/a[8]').xpath('//@paged')
${extract.selectors(resp.html,'.pagination > a:nth-child(9)','attr','paged')}
.pagination > a:nth-child(9)
${extract.selectors(resp.html,'.pagination > a:nth-child(9)','attr','paged')}

document.querySelector("#page_6791341 > a:nth-child(9)")
j-fontContent

sel.xpath('//ul[@class="doc_list"]/li/a//span/text()')
#page_6791341 > a:nth-child(9)

https://api.zhihu.com/search_v3?advert_count=0&correction=1&lc_idx=0&limit=20&offset=20&q=%E7%B2%BE%E8%87%B4%E7%A9%B7&search_hash_id=391b9d2f5a38790e0d8b03d3fb591d97&show_all_topics=0&t=general&vertical_info=0%2C0%2C1%2C0%2C0%2C0%2C0%2C0%2C0%2C1
//*[@id="color_printsssss"]/div[1]/div[1]
#color_printsssss > div.newsinfo.clearfix > div.newsinfl_left.fl
${extract.selector(resp.html,'#color_printsssss > div.newsinfo.clearfix > div.newsinfl_left.fl','text')}


#color_printsssss > div.j-fontContent.newscontnet.minh500 > table > tbody > tr:nth-child(2) > td:nth-child(1)

#color_printsssss > div.j-fontContent.newscontnet.minh500 > table > tbody > tr:nth-child(3) > td:nth-child(2)

document.querySelector("#color_printsssss > div.j-fontContent.newscontnet.minh500 > table > tbody > tr:nth-child(1) > td:nth-child(1)")

#color_printsssss > div.j-fontContent.newscontnet.minh500 > table > tbody > tr:nth-child(1) > td:nth-child(1)

//*[@id="color_printsssss"]/div[2]/table/tbody/tr[3]/td[1]
#color_printsssss > div.j-fontContent.newscontnet.minh500 > table > tbody > tr:nth-child(3) > td:nth-child(1)

#color_printsssss > div.j-fontContent.newscontnet.minh500 > table > tbody > tr:nth-child(1) > td:nth-child(1)

 div.rightnr.j-dg-right > div.listnews > ul > li:nth-child(1) > span

/html/body/div[4]/div/div/div[2]/div[3]/div[2]/ul/li[1]/span

body > div.container > div > div > div.clearfix.lmcontent.mt20 > div.rightnr.j-dg-right > div.listnews > ul > li:nth-child(1) > span

${extract.selector(resp.html,'div.listnews > ul > li:nth-child(1) > span','text')}

${resp.xpaths('//div[@class="listnews"]/li//span/text()')}

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值