# coding=utf-8
import requestsimport jsonfrom retrying import retryimport re class TyY: def __init__(self): self.url = ["http://www.tylaw.cn/cgi-bin/GLaw.dll?DispInfo&nid={}".format(i) for i in range(3723, 3752)] self.headers = { "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.75 Safari/537.36" }@retry(stop_max_attempt_number=3) # 设置最大请求连接数
def _parse_url(self, url):response = requests.get(url, headers=self.headers, timeout=3)
assert response.status_code == 200 response.encoding = "gb2312" return response.textdef parse_url(self, url):
try: html = self._parse_url(url) except: html = None return htmldef get_content_list(self, html):
content_list = [] item = {}item['name'] = re.findall(r"<p align='center' class='titlc'>.*?律师:(.*?)简介.*?</p>", html, re.S)[0] if len(re.findall(r"<p align='center' class='titlc'>.*?律师:(.*?)简介.*?</p>", html, re.S)) > 0 else None
item['email'] = re.findall(r"<div class='contc'>.*?【电子信箱】(.*?) </div>", html, re.S)[0] if len(re.findall(r"<div class='contc'>.*?【电子信箱】(.*?) </div>", html, re.S)) > 0 else None content_list.append(item)# print(item)
return content_listdef save_content(self, content_list):
with open("tyy.json", "a") as f: for content in content_list: json.dump(content, f, ensure_ascii=False) f.write(',\n')def run(self):
url_list = self.url for url in url_list: html = self.parse_url(url) content_list = self.get_content_list(html) self.save_content(content_list)if __name__ == '__main__': tyy = TyY() tyy.run()