爬取西宁的天气信息（Python）

import requests
import re  # 正则表达式操作
import xlwt




def getHTMLText(url):  # 得到网页文件
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding  # 转换编码格式
        return r.text
    except Exception as e:
        print(str(e))


def parsePage(ilt, html):  # 分析页面函数得到相应的值
    try:
        ymd = re.findall("ymd:'(.*?)',", html)
        high = re.findall("bWendu:'(.*?)℃',", html)
        low = re.findall("yWendu:'(.*?)℃',", html)
        tianqi = re.findall("tianqi:'(.*?)',", html)
        fengxiang = re.findall("fengxiang:'(.*?)',", html)
        fengli = re.findall(",fengli:'(.*?)'", html)
        aqi = re.findall("aqi:'(.*?)',", html)
        aqiInfo = re.findall("aqiInfo:'(.*?)',", html)
        aqiLevel = re.findall(",aqiLevel:'(.*?)'", html)
        # 应为日期是每一天都有的，所以可以作为基准，以此来遍历
        for i in range(len(ymd)):  # 将每一天的信息保存为一个列表
            data = ymd[i]
            maxTem = high[i]
            minTem = low[i]
            weather = tianqi[i]
            windDirection = fengxiang[i]
            windLev = fengli[i]
            airNum = aqi[i]
            airEva = aqiInfo[i]
            airLev = aqiLevel[i]
            ilt.append([data, maxTem, minTem, weather, windDirection, windLev, airNum, airEva, airLev])
    except:
        print("异常")


def printGoodsList(ilt):  # 字符串的格式化处理
    xiNing = xlwt.Workbook()
    sheet1 = xiNing.add_sheet("sheet1")
    """ 
    rule = "{:8}\t{:3}\t{:3}\t{:8}\t{:8}\t{:6}\t{:4}\t{:2}\t{:6}"  # 字符串的格式化
    print(rule.format("data", "maxTem", "minTem", "weather", "windDirection", "windLev", "airNum", "airEva", "airLev"))
     # 还需要改进的代码
    for i in range(len(ilt)):
        print(rule.format(ilt[i][0], ilt[i][1], ilt[i][2], ilt[i][3], ilt[i][4], ilt[i][5], ilt[i][6], ilt[i][7], ilt[i][8]))
    """
    for i in range(len(ilt)):
        for j in range(len(ilt[i])):
            sheet1.write(i, j, ilt[i][j])
    xiNing.save("西宁.xls")



if __name__ == "__main__":
    start_url = "http://tianqi.2345.com/t/wea_history/js/"
    list0 = []
    list0.append(["日期", "最高气温", "最低气温", "天气", "风向", "风力", "空气质量指数", "空气质量评价", "空气质量等级"])
    #根据观察，发现有的日期的格式有点奇怪，所以分开处理
    for i in range(2016, 2019):  # 左闭右开
        try:
            if i == 2018:
                for j in range(1, 5):  # 1-4月
                    url = start_url + str(i) + "0" + str(j) + "/52866_" + str(i) + "0" + str(j) + ".js"
                    html = getHTMLText(url)
                   # print(html)  #网址没有错，且能访问成功
                    parsePage(list0, html)  # 调用函数的时候，列表的值岁随函数里面的变化而变化
            elif i == 2016:
                for j in range(1, 13):  # 1-12月
                    if j in range(3, 10):
                        url = start_url + str(i) + "0" + str(j) + "/52866_" + str(i) + "0" + str(j) + ".js"
                    elif j in range(1, 3):
                        url = start_url + "/52866_" + str(i) + str(j) + ".js"
                    else:
                        url = start_url + str(i) + str(j) + "/52866_" + str(i) + str(j) + ".js"
                    html = getHTMLText(url)
                    #print(html)
                    parsePage(list0, html)
            else:
                for j in range(1, 13):
                    if j in range(1, 10):
                        url = start_url + str(i) + "0" + str(j) + "/52866_" + str(i) + "0" + str(j) + ".js"
                    else:
                        url = start_url + str(i) + str(j) + "/52866_" + str(i) + str(j) + ".js"
                    html = getHTMLText(url)
                   # print(html)
                    parsePage(list0, html)
        except:
            continue
    #print(len(list0))
    printGoodsList(list0)

欢迎大家来指教