python可视化操作（二）爬取湖北省统计局数据绘制excel表格

在这里写了一个比较简单的爬虫，爬取了湖北省统计局关于居民消费价格指数的一些简单信息，然后绘制成excel表格输出。一来是为了复习一下爬虫的简单知识，一是为了熟悉一下python操作excel的技术。

转换成功之后

#http://data.stats.gov.cn/easyquery.htm?cn=G0103
from urllib.request import urlopen
from bs4 import BeautifulSoup
import xlwt

def crawl():
    #打开网页
    html = urlopen("http://data.hb.stats.cn/CityData.aspx?DataType=65&ReportType=1")
    bsObj = BeautifulSoup(html.read(), "html5lib")

    titles = []
    for title in bsObj.find("tr", {"class":"tr-title"}).find_all("td"):
        titles.append(title.getText())
    # datas = []
    # for data in bsObj.find("tr", {"class":"tr-title"}).find("")
    print (titles)


    datas = []
    dd = []
    for data in bsObj.find_all("tr", {"class":"tr-title"}):
        for d in data.find_all("td"):
            dd.append(d.getText())
        datas.append(dd)
        dd = []    
    print (datas)
    return datas

def set_style(name, height, bold = False):
    style = xlwt.XFStyle() #初始化样式
    font = xlwt.Font() #为样式创建字体
    font.name = name
    font.bold = bold
    font.color_index = 4
    font.height = height
    style.font = font
    return style

def write_excel():
    #创建工作簿
    workbook = xlwt.Workbook(encoding="utf-8")
    #创建sheet
    data_sheet = workbook.add_sheet("show_data")

    datas = crawl()

    index = 0
    for i in datas:
        for x, item in enumerate(i):
            data_sheet.write(index, x, item, set_style('Times New Roman',220, True))
        index += 1

    workbook.save("data.xls")


if __name__ == '__main__':
    write_excel()
    print("创建你xlsx文件成功")