python 爬取天气预报

先在中国天气网中搜索南京天气,打开南京天气页面,从地址栏中的的到url,按F12,选择Elements

在Elements中移动鼠标,查找天气内容所在div:

展开div后,可以看到每天的天气信息就在ul下的li中.

所以,整体思路就是:
1.先根据url拿到整个页面的内容.
2.在内容中,先找到对应的div,然后再找到对应的ul,最后遍历所有的li拿到天气信息.

代码如下:



import requests
import bs4

#获取网页内容
def get_content(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'}

    try:
        html = requests.get(url, headers = headers)
        html.encoding = "utf-8"
        content = html.text
    except Exception as e:
        print(e)
        return None

    return content

#从网页内容中获取天气信息
def get_weather(content):
    final = []
    bs = bs4.BeautifulSoup(content, "lxml")
    data = bs.find("div",{"id":"7d"})  #先找到对应的div
    ul = data.find("ul")    #再从div中找到ul
    li = ul.find_all("li")  #从ul中获取所有li

    #遍历li,拿到每天的天气信息.
    for day in li:
        temp=[]
        date=day.find("h1").string
        temp.append(date)
        inf=day.find_all("p")
        temp.append(inf[0].string)
        if inf[1].find("span") is None:
            temperature_high=None
        else:
            temperature_high = inf[1].find("span").string
            temperature_high = "最高温度: " + temperature_high

        temperature_lower = inf[1].find("i").string
        temperature_lower = temperature_lower.replace("℃","")
        temperature_lower =  "最低温度: " + temperature_lower
        temp.append(temperature_high)
        temp.append(temperature_lower)
        final.append(temp)

    return final

if __name__=="__main__":
    url = "http://www.weather.com.cn/weather/101190101.shtml"
    content = get_content(url)

    if content is None:
        print("get content fail")
    else:
        weather = get_weather(content)
        print("南京天气:")
        for we in weather:
            print(we)

运行结果: