爬中国天气网遇到的一些问题

Question

1. import requests
   from bs4 import BeautifulSoup
   from pyecharts.charts import Bar
   
   ALL_DATA = []
   
   def parse_page(url,jiex):
       header = {
           'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; '
                         'Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36',
           # 'Referer': 'http://www.weather.com.cn/textFC/hb.shtml'
       } # 模拟浏览器
       response = requests.get(url=url, headers=header) # 发送get命令
       text = response.content.decode('utf-8')
       # text用requests库获取
       soup = BeautifulSoup(text,jiex) # 以lxml方式解析
       conMidtab = soup.find('div',class_='conMidtab')
       tables = conMidtab.find_all('table')
       for table in tables:
           trs = table.find_all('tr')[2:]
           for tr in trs:
               tds = tr.find_all('td')
               chengs = list(tds[-8].stripped_strings)[0] # 倒数第8列为城市信息
               maxtemp = list(tds[-5].stripped_strings)[0] # 倒数第5列为最高气温
               mintemp = list(tds[-2].stripped_strings)[0] # 倒数第2列为最低气温
               ALL_DATA.append({"城市":chengs,"最高气温":int(maxtemp),"最低气温":int(mintemp)})
   
   def main():
       urls = {
           'http://www.weather.com.cn/textFC/hb.shtml',
           'http://www.weather.com.cn/textFC/db.shtml',
           'http://www.weather.com.cn/textFC/hd.shtml',
           'http://www.weather.com.cn/textFC/hz.shtml',
           'http://www.weather.com.cn/textFC/hn.shtml',
           'http://www.weather.com.cn/textFC/xb.shtml',
           'http://www.weather.com.cn/textFC/xn.shtml'
       }
       for url in urls:
           parse_page(url,'lxml')
       url_gat = 'http://www.weather.com.cn/textFC/gat.shtml'
       parse_page(url_gat,'html5lib')#容错能力强的html5lib对港澳台进行解析
   
       # 分析数据
       ALL_DATA.sort(key=lambda data:data["最低气温"])
       min_data = ALL_DATA[:10]
       ALL_DATA.sort(key=lambda data:data["最高气温"])
       max_data = ALL_DATA[-10:-1]
       # 数据可视化
       cities_min = list(map(lambda x:x["城市"], min_data))
       cities_max = list(map(lambda x:x["城市"], max_data))
       min_temp = list(map(lambda x:x["最低气温"], min_data))
       max_temp = list(map(lambda x: x["最高气温"], max_data))
   
       bar1 = Bar()
       bar1.add_xaxis(cities_min)
       bar1.add_yaxis("气温/℃", min_temp)
       bar1.set_global_opts(title_opts={"text": "中国城市气温排行榜", "subtext": "最低气温"})
       bar1.render("最低气温.html")
       bar2 = Bar()
       bar2.add_xaxis(cities_max)
       bar2.add_yaxis("气温/℃", max_temp)
       bar2.set_global_opts(title_opts={"text": "中国城市气温排行榜", "subtext": "最高气温"})
       bar2.render("最高气温.html")
   
   
   if __name__ == '__main__':
       main()

然后出现了以下问题，求大神指点

我应该怎么改

Answer 1

需要安装解析器html5lib库，先配置好环境变量，执行语句 pip install html5lib 安装。另外代码如不用html5lib解析的话，用其他解析器解析内容不全，会出现索引越界错误。

如对解答满意，请点一下采纳。