# 从化妆品资讯网查询新闻列表
# 通过调用企业微信机器接口推送到群里
# 先引入功能库
import requests
import bs4# 自定义一个请求函数，参数是网址请求头请求参数，没有参数就空着，请求成功后返回页面的新闻列表
def catchnewslist(newsurl, headers, params):urllist = []titlelist = []resultlist = []response = requests.get(newsurl, headers=headers)if response.status_code == 200:print("请求成功！")response.encoding = 'utf-8'content = bs4.BeautifulSoup(response.text, 'html.parser')elements = content.select("#content h1 a")               # 这一句就是提取请求到的页面内容中要提取的新闻，根据不同的页面结构进行修改for element in elements:                                 # 把取到的新闻列表数据存到一个python列表中，方便后面使用urllist.append("http://www.cosmetic-news.net/" + element.get('href'))titlelist.append(element.string)resultlist = [[a, b] for a, b in zip(urllist, titlelist)]   # 把标题和地址组合成一个嵌套列表，并返回else:print(response.status_code)print("请求失败！")return resultlist# 定义一个向企业微个webhook地址post数据的函数，参数为地址和数据，这里post的是md5格式的字符串
def postmsg(url, post_data):post_data = '{"msgtype":"markdown","markdown":{"content":"%s"}}' % post_data# print(post_data)if url == '':print('url is blank')else:r = requests.post(url, data=post_data.encode())rstr = r.json()if r.status_code == 200 and 'error' not in rstr:result = 'success!'return resultelse:return 'Error'# 主函数
if __name__ == '__main__':newsurl = "http://www.cosmetic-news.net/newx-4.html"headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.92 Safari/537.36"}# params = {"datatype":"jsonp", "page":"1", "callback":"flightHandler"}  参数视需求添加newslist = catchnewslist(newsurl, headers, '')# print(newslist)# 把请求回来的数据，按照要post到接口的md的格式再处理一下newslistdata = u"### 近期行业资讯： n"for i in newslist:# print("[%s](%s)" % (i[1], i[0]))newslistdata = newslistdata + "%s [%s](%s)" % (newslist.index(i) + 1, i[1], i[0]) + "n"print(newslistdata)url = "https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=********-****-****-****-**********"   # 要post的群机器人的webhook地址# post_data = '[这是一个链接](http://work.weixin.qq.com/api/doc)' # 带链接的md字符串格式result = postmsg(url, newslistdata)  # 调用post，向webhook发送数据print(result)