爬取中国天气网 | 对最低温排名前十城市进行可视化
可视化需要用的的库：
from pyecharts.charts import Bar from pyecharts import options as opts
可视化的核心代码：
# 原有的这 个方式无效了 # chart = Bar({"中国天气最低气温排行榜"}) # chart.add('',cities,temps) # chart.render('temperature.html') chart = Bar() chart.add_xaxis(cities) chart.add_yaxis("城市",temps) chart.set_global_opts(title_opts=opts.TitleOpts(title="中国天气最低气温排行榜")) chart.render('temperature.html')
#encoding: utf-8 import requests from bs4 import BeautifulSoup from pyecharts.charts import Bar from pyecharts import options as opts ''' pyecharts 用来画图表的，bar:柱状图 ''' ALL_DATA = [] def parse_page(url): headers = { 'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36" } response = requests.get(url,headers=headers) text = response.content.decode('utf-8') # html5lib # pip install html5lib soup = BeautifulSoup(text,'html5lib') conMidtab = soup.find('div',class_='conMidtab') tables = conMidtab.find_all('table') for table in tables: trs = table.find_all('tr')[2:] for index,tr in enumerate(trs): tds = tr.find_all('td') city_td = tds[0] if index == 0: city_td = tds[1] city = list(city_td.stripped_strings)[0] temp_td = tds[-2] min_temp = list(temp_td.stripped_strings)[0] ALL_DATA.append({"city":city,"min_temp":int(min_temp)}) print({"city":city,"min_temp":int(min_temp)}) 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', 'http://www.weather.com.cn/textFC/gat.shtml' ] for url in urls: parse_page(url) # 分析数据 # 根据最低气温进行排序 ALL_DATA.sort(key=lambda data:data['min_temp']) data = ALL_DATA[0:10] cities = list(map(lambda x:x['city'],data)) temps = list(map(lambda x:x['min_temp'],data)) # pyecharts # pip install pyecharts # 原有的这 个方式无效了 # chart = Bar({"中国天气最低气温排行榜"}) # chart.add('',cities,temps) # chart.render('temperature.html') chart = Bar() chart.add_xaxis(cities) chart.add_yaxis("城市",temps) chart.set_global_opts(title_opts=opts.TitleOpts(title="中国天气最低气温排行榜")) chart.render('temperature.html') if __name__ == '__main__': main() # ALL_DATA = [ # {"city": "北京", 'min_temp': 0}, # {"city": "天津", 'min_temp': -8}, # {"city": "石家庄", 'min_temp': -10} # ] # # ALL_DATA.sort(key=lambda data:data['min_temp']) # print(ALL_DATA)
<!DOCTYPE html>
<html>
<head>
<meta charset="UTF-8">
<title>Awesome-pyecharts</title>
<script type="text/javascript" src="https://assets.pyecharts.org/assets/echarts.min.js"></script>
</head>
<body>
<div id="8d8789eafca0473299441d8a914fe0d0" class="chart-container" style="width:900px; height:500px;"></div>
<script>
var chart_8d8789eafca0473299441d8a914fe0d0 = echarts.init(
document.getElementById('8d8789eafca0473299441d8a914fe0d0'), 'white', {renderer: 'canvas'});
var option_8d8789eafca0473299441d8a914fe0d0 = {
"animation": true,
"animationThreshold": 2000,
"animationDuration": 1000,
"animationEasing": "cubicOut",
"animationDelay": 0,
"animationDurationUpdate": 300,
"animationEasingUpdate": "cubicOut",
"animationDelayUpdate": 0,
"color": [
"#c23531",
"#2f4554",
"#61a0a8",
"#d48265",
"#749f83",
"#ca8622",
"#bda29a",
"#6e7074",
"#546570",
"#c4ccd3",
"#f05b72",
"#ef5b9c",
"#f47920",
"#905a3d",
"#fab27b",
"#2a5caa",
"#444693",
"#726930",
"#b2d235",
"#6d8346",
"#ac6767",
"#1d953f",
"#6950a1",
"#918597"
],
"series": [
{
"type": "bar",
"name": "\u57ce\u5e02",
"data": [
4,
6,
6,
6,
6,
7,
8,
8,
8,
9
],
"barCategoryGap": "20%",
"label": {
"show": true,
"position": "top",
"margin": 8
}
}
],
"legend": [
{
"data": [
"\u57ce\u5e02"
],
"selected": {
"\u57ce\u5e02": true
},
"show": true
}
],
"tooltip": {
"show": true,
"trigger": "item",
"triggerOn": "mousemove|click",
"axisPointer": {
"type": "line"
},
"textStyle": {
"fontSize": 14
},
"borderWidth": 0
},
"xAxis": [
{
"show": true,
"scale": false,
"nameLocation": "end",
"nameGap": 15,
"gridIndex": 0,
"inverse": false,
"offset": 0,
"splitNumber": 5,
"minInterval": 0,
"splitLine": {
"show": false,
"lineStyle": {
"width": 1,
"opacity": 1,
"curveness": 0,
"type": "solid"
}
},
"data": [
"\u679c\u6d1b",
"\u7389\u6811",
"\u6d77\u5317",
"\u90a3\u66f2",
"\u963f\u91cc",
"\u963f\u575d",
"\u5927\u540c",
"\u7518\u5357",
"\u8fea\u5e86",
"\u77f3\u6cb3\u5b50"
]
}
],
"yAxis": [
{
"show": true,
"scale": false,
"nameLocation": "end",
"nameGap": 15,
"gridIndex": 0,
"inverse": false,
"offset": 0,
"splitNumber": 5,
"minInterval": 0,
"splitLine": {
"show": false,
"lineStyle": {
"width": 1,
"opacity": 1,
"curveness": 0,
"type": "solid"
}
}
}
],
"title": [
{
"text": "\u4e2d\u56fd\u5929\u6c14\u6700\u4f4e\u6c14\u6e29\u6392\u884c\u699c"
}
]
};
chart_8d8789eafca0473299441d8a914fe0d0.setOption(option_8d8789eafca0473299441d8a914fe0d0);
</script>
</body>
</html>
