遇到list index out of range的解决办法

怡宁2131

1. #-*- codeing=utf-8 -*-
   
2. import re
   
3. from bs4 import BeautifulSoup
   
4. import urllib.request
   
5. import region       #此库为地区编码(有芒市，昆明，保山)
   
6. 
   
7. 
   
8. def main():
   
9.     baseurl="http://www.weather.com.cn/"
   
10.     datalist=getData(baseurl)
    
11.     print(datalist)
    
12.    
    
13. 
    
14. #设置获取规则(规则相同的同一归为Allrule1和Allrule2)
    
15. Allrule1=re.compile(r'<span>(.*)</span>')      
    
16. Allrule2=re.compile(r'<em>(.*)</em>')
    
17. findwindclassAct=Allrule2
    
18. findtempAct=Allrule1
    
19. findActtime=Allrule1
    
20. findhumAct=Allrule2
    
21. findwinddirAct=Allrule1
    
22. 
    
23. findinqDay=re.compile(r'<p class="wea" title="(.*)">(.*)</p>')
    
24. findtempDay=Allrule1
    
25. findwinddirDay=re.compile(r'<span class title="(.*)">')
    
26. findwindclassDay=re.compile(r'<(.*)</span>')
    
27. findsunriTime=Allrule1
    
28. 
    
29. findinqNight=re.compile(r'<p class="wea" title="(.*)">(.*)</p>')
    
30. findtempNight=Allrule1
    
31. findwinddirNight=re.compile(r'<span class title="(.*)">')
    
32. findwindclassNight=re.compile(r'<(.*)</span>')
    
33. sunsetTime=Allrule1
    
34. 
    
35. 
    
36. 
    
37. #爬取网页
    
38. def getData(baseurl):
    
39.     regionnum=region.selectRegion()
    
40.     url=baseurl+r"weather1d/"+regionnum+".shtml#around1"
    
41.     html=askUrl(url)
    
42.     #解析数据
    
43.     soup=BeautifulSoup(html,"html.parser")
    
44.     for item in soup.find_all('div',class_="t"):
    
45.         data=[]
    
46.         item=str(item)
    
47. 
    
48.         
    
49.         Acttime=re.findall(findActtime,item)[0]             #获取当前时间
    
50.         data.append(Acttime)                                
    
51.         tempAct=re.findall(findtempAct,item)[3]             #获取当前气温
    
52.         data.append(tempAct)
    
53.         humAct=re.findall(findhumAct,item)[0]               #获取当前湿度
    
54.         data.append(humAct)
    
55.         winddirAct=re.findall(findwinddirAct,item)[2]       #获取当前风向
    
56.         data.append(winddirAct)
    
57.         windclassAct=re.findall(findwindclassAct,item)[1]   #获取当前风力级别
    
58.         data.append(windclassAct)                           
    
59. 
    
60.         inqDay=re.findall(findinqDay,item)[0]               #获取白天天气种类
    
61.         data.append(inqDay)
    
62.         tempDay=re.findall(findtempDay,item)[5]             #获取白天气温
    
63.         data.append(tempDay)
    
64.         winddirDay=re.findall(findwinddirDay,item)[0]       #获取白天风向
    
65.         data.append(winddirDay)
    
66.         windclassDay=re.findall(findwindclassDay,item)[0]   #获取白天风力级别
    
67.         data.append(windclassDay)
    
68.         sunriTime=re.findall(findsunriTime,item)[6]         #获取日出时间
    
69.         data.append(sunriTime)
    
70. 
    
71.         inqNight=re.findall(findinqNight,item)[1]           #获取夜间天气种类
    
72.         data.append(inqNight)
    
73.         tempNight=re.findall(findtempNight,item)[7]         #获取夜间气温
    
74.         data.append(tempNight)
    
75.         winddirNight=re.findall(findwinddirNight,item)[1]   #获取夜间风向
    
76.         data.append(winddirNight)
    
77.         windclassNight=re.findall(findwindclassNight,item)[1] #获取夜间风力级别
    
78.         data.append(windclassNight)
    
79.         sunsetTime=re.findall(findsunsetTime,item)[8]       #获取日落时间
    
80.         data.append(sunsetTime)
    
81. 
    
82.         
    
83.     return data
    
84. 
    
85. 
    
86. """
    
87. def printData():
    
88.     data=getData(baseurl)
    
89.     print(data)
    
90. """   
    
91. 
    
92. 
    
93. #获取网页
    
94. def askUrl(url):
    
95.     head={
    
96.         "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.54 Safari/537.36"
    
97.     }
    
98.     req=urllib.request.Request(url,headers=head)
    
99.     html=""
    
100.     try:
     
101.         resp=urllib.request.urlopen(req)
     
102.         html=resp.read().decode("utf-8")
     
103. 
     
104.     except urllib.error.URLError as e:
     
105.         if hasattr(e,"code"):
     
106.             print(e.code)
     
107.         if hasattr(e,"reason"):
     
108.             print(e.reason)
     
109.    
     
110.     return html
     
111. 
     
112. 
     
113. 
     
114. if __name__=="__main__":
     
115.     main()

复制代码

------------------------------------
报错信息为:
Traceback (most recent call last):
  File "F:\python_file\spider_wether.py", line 115, in <module>
    main()
  File "F:\python_file\spider_wether.py", line 10, in main
    data=getData(baseurl)
  File "F:\python_file\spider_wether.py", line 63, in getData
    winddirDay=re.findall(findwinddirDay,item)[0]
IndexError: list index out of range
------------------------------------
求助求助求助求助

suchocolate

winddirDay=re.findall(findwinddirDay,item)[0] 这一行没有找到数据，所以报错了，查查re语法，一般都用非贪婪匹配的。