用Python爬取电影数据并可视化分析_python电影数据分析

---

一、获取数据

1.技术工具

IDE编辑器：vscode

发送请求：requests

解析工具：xpath

def Get_Detail(Details_Url):
    Detail_Url = Base_Url + Details_Url
    One_Detail = requests.get(url=Detail_Url, headers=Headers)
    One_Detail_Html = One_Detail.content.decode('gbk')
    Detail_Html = etree.HTML(One_Detail_Html)
    Detail_Content = Detail_Html.xpath("//div[@id='Zoom']//text()")
    Video_Name_CN,Video_Name,Video_Address,Video_Type,Video_language,Video_Date,Video_Number,Video_Time,Video_Daoyan,Video_Yanyuan_list = None,None,None,None,None,None,None,None,None,None
    for index, info in enumerate(Detail_Content):
        if info.startswith('◎译　　名'):
            Video_Name_CN = info.replace('◎译　　名', '').strip()
        if info.startswith('◎片　　名'):
            Video_Name = info.replace('◎片　　名', '').strip()
        if info.startswith('◎产　　地'):
            Video_Address = info.replace('◎产　　地', '').strip()
        if info.startswith('◎类　　别'):
            Video_Type = info.replace('◎类　　别', '').strip()
        if info.startswith('◎语　　言'):
            Video_language = info.replace('◎语　　言', '').strip()
        if info.startswith('◎上映日期'):
            Video_Date = info.replace('◎上映日期', '').strip()
        if info.startswith('◎豆瓣评分'):
            Video_Number = info.replace('◎豆瓣评分', '').strip()
        if info.startswith('◎片　　长'):
            Video_Time = info.replace('◎片　　长', '').strip()
        if info.startswith('◎导　　演'):
            Video_Daoyan = info.replace('◎导　　演', '').strip()
        if info.startswith('◎主　　演'):
            Video_Yanyuan_list = []
            Video_Yanyuan = info.replace('◎主　　演', '').strip()
            Video_Yanyuan_list.append(Video_Yanyuan)
            for x in range(index + 1, len(Detail_Content)):
                actor = Detail_Content