python爬虫+数据可视化项目（关注、

 1 import requests
 2 from bs4 import BeautifulSoup
 3 from pyecharts import Bar
 4 
 5 ALL_DATA = []
 6 def send_parse_urls(start_urls):
 7     headers = {
 8     "User-Agent": "Mozilla/5.0 (compatible; YandexBot/3.0; +http://yandex.com/bots)"
 9     }
10     for start_url in start_urls:
11         response = requests.get(start_url,headers=headers)
12         # 编码问题的解决
13         response = response.text.encode("raw_unicode_escape").decode("utf-8")
14         soup = BeautifulSoup(response,"html5lib") #lxml解析器：性能比较好，html5lib：适合页面结构比较混乱的
15         div_tatall = soup.find("div",class_="conMidtab") #find() 找符合要求的第一个元素
16         tables = div_tatall.find_all("table") #find_all() 找到符合要求的所有元素的列表
17         for table in tables:
18             trs = table.find_all("tr")
19             info_trs = trs[2:]
20             for index,info_tr in enumerate(info_trs): # 枚举函数，可以获得索引
21                 # print(index,info_tr)
22                 # print("="*30)
23                 city_td = info_tr.find_all("td")[0]
24                 temp_td = info_tr.find_all("td")[6]
25                 # if的判断的index的特殊情况应该在一般情况的后面，把之前的数据覆盖
26                 if index==0:
27                     city_td = info_tr.find_all("td")[1]
28                     temp_td = info_tr.find_all("td")[7]
29                 city=list(city_td.stripped_strings)[0]
30                 temp=list(temp_td.stripped_strings)[0]
31                 ALL_DATA.append({"city":city,"temp":temp})
32     return ALL_DATA
33 
34 def get_start_urls():
35     start_urls = [
36        "http://www.weather.com.cn/textFC/hb.shtml",
37         "http://www.weather.com.cn/textFC/db.shtml",
38         "http://www.weather.com.cn/textFC/hd.shtml",
39         "http://www.weather.com.cn/textFC/hz.shtml",
40         "http://www.weather.com.cn/textFC/hn.shtml",
41         "http://www.weather.com.cn/textFC/xb.shtml",
42         "http://www.weather.com.cn/textFC/xn.shtml",
43         "http://www.weather.com.cn/textFC/gat.shtml",
44     ]
45     return start_urls
46 
47 def main():
48     """
49     主程序逻辑
50     展示全国实时温度最低的十个城市气温排行榜的柱状图
51     """
52     # 1 获取所有起始url
53     start_urls = get_start_urls()
54     # 2 发送请求获取响应、解析页面
55     data = send_parse_urls(start_urls)
56     # print(data)
57     # 4 数据可视化
58         #1排序
59     data.sort(key=lambda data:int(data["temp"]))
60         #2切片，选择出温度最低的十个城市和温度值
61     show_data = data[:10]
62         #3分出城市和温度
63     city = list(map(lambda data:data["city"],show_data))
64     temp = list(map(lambda data:int(data["temp"]),show_data))
65         #4创建柱状图、生成目标图
66     chart = Bar("中国最低气温排行榜") #需要安装pyechart模块
67     chart.add("",city,temp)
68     chart.render("tempture.html")
69 
70 if __name__ == '__main__':
71     main()