import requests import re file = open("vocabulary.doc", "w", encoding="utf-8") def spider(url): res = requests.get(url).text pattern = '<strong>([a-z,A-Z]*?)</strong>\s*</td>\s*<td class="span10">(.*?)</td>' vocabulary_list = re.findall(pattern, res) for vocabulary in vocabulary_list: file.writelines((vocabulary[0].strip(''), vocabulary[1].strip(''), "\n")) url_list = ["https://www.shanbay.com/wordlist/104899/202159/?page=", "https://www.shanbay.com/wordlist/104899/202162/?page=", ] for url in url_list: for i in range(1, 10): url = "https://www.shanbay.com/wordlist/104899/202159/?page=" + str(i) spider(url) file.close()
# 太实诚了,先放了源码,几行代码,纯粹是免登陆,免199贝壳去支付...拿下网页的单词
# 会生成一个word的结果文档在代码运行的同一目录下,结果如下,没有可以排版,最好是放在excel下。