xpath爬个扇贝单词

 注意的是：

//     是全局查找

.//   是当前节点标签内全局查找

提示：

有多少页单词就能爬多少页，就是用这几行代码跳出死循环的，也就是说说捕获不到数据就说明页码到头了。

tr_list = tree.xpath('//table[@class="table table-bordered table-striped"]/tbody/tr')

    if not tr_list:
        break

import requests
from lxml import etree

def getData(list):
    if len(list) > 0 :
        return list[0]
    else:
        return ''
# url = 'https://www.shanbay.com/wordlist/110521/232414/'
# url2 ='https://www.shanbay.com/wordlist/110521/232414/?page=2'
headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.108 Safari/537.36'
}
page = 1
while True:
    url = 'https://www.shanbay.com/wordlist/110521/232414/?page={}'.format(page)
    page += 1
    response = requests.request('get',url=url,headers=headers)

    with open('word.html','w',encoding=response.encoding)as fp:
        fp.write(response.text)

    tree = etree.HTML(response.text)
    # //是全局查找
    tr_list = tree.xpath('//table[@class="table table-bordered table-striped"]/tbody/tr')

    if not tr_list:
        break

    for tr in tr_list:
        word_list = tr.xpath('.//strong/text()')
        word = getData(word_list)
        # .//是当前标签内全局查找
        meaning_list = tr.xpath('.//td[@class="span10"]/text()')
        meaning = getData(meaning_list)
        print(word,meaning)