1 import requests 2 import re 3 from lxml import etree 4 5 headers = 'Mozilla/5.0 (Windows NT 10.0; …) Gecko/20100101 Firefox/60.0' 6 7 8 def get_html(url): 9 try:10 response = requests.get(url, headers)11 response.raise_for_status()12 response.encoding = 'utf-8'13 return response.text14 except:15 print('get_html() faild')16 17 18 def parse_html(html):19 # 正则表达式20 hrefs = re.findall(r'(.*?)', html, re.S)26 27 new_content = []28 for content in contents:29 content = re.sub('<.*?>', '', content)30 x = content.strip()31 new_content.append(x)32 return new_content33 34 35 def main():36 page_num = 1337 for i in range(1, page_num+1):38 url = 'https://www.qiushibaike.com/text/page/{}/'.format(i)39 html = get_html(url)40 contents = parse_html(html)41 print(contents)42 43 44 if __name__ == '__main__':45 main() hrefs = re.findall(r'
这个链接的正则表达式感觉写的没问题啊，可是匹配不到东西，奇了怪了，先放着吧，xpath可以匹配到
运行结果
