Python如何爬取b站熱門視訊並匯入Excel
阿新 • • 發佈:2020-08-12
程式碼如下
#encoding:utf-8 import requests from lxml import etree import xlwt import os # 爬取b站熱門視訊資訊 def spider(): video_list = [] url = "https://www.bilibili.com/ranking?spm_id_from=333.851.b_7072696d61727950616765546162.3" html = requests.get(url,headers={"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML,like Gecko) Chrome/75.0.3770.100 Safari/537.36"}).text html = etree.HTML(html) infolist = html.xpath("//li[@class='rank-item']") for item in infolist: rank = "".join(item.xpath("./div[@class='num']/text()")) video_link = "".join(item.xpath(".//div[@class='info']/a/@href")) title = "".join(item.xpath(".//div[@class='info']/a/text()")) payinfo = "".join(item.xpath(".//div[@class='detail']/span/text()")).split("萬") play = payinfo[0] + "萬" comment = payinfo[1] if comment.isdigit() == False: comment += "萬" upname = "".join(item.xpath(".//div[@class='detail']/a/span/text()")) uplink = "http://" + "".join(item.xpath(".//div[@class='detail']/a/@href")) hot = "".join(item.xpath(".//div[@class='pts']/div/text()")) video_list.append({ 'rank': rank,'videolink': video_link,'title': title,'play': play,'comment': comment,'upname': upname,'uplink': uplink,'hot': hot }) return video_list def write_Excel(): # 將爬取的資訊新增到Excel video_list = spider() workbook = xlwt.Workbook() # 定義表格 sheet = workbook.add_sheet("b站熱門視訊") # 新增sheet的name xstyle = xlwt.XFStyle() # 例項化表格樣式物件 xstyle.alignment.horz = 0x02 # 字型居中 xstyle.alignment.vert = 0x01 head = ['視訊名','up主','排名','熱度','播放量','評論數'] for h in range(len(head)): sheet.write(0,h,head[h],xstyle) i = 1 for item in video_list: # 向單元格(視訊名)新增該視訊的超連結 if '"' in item["title"]: item["title"] = item["title"].split('"')[1] title_data = 'HYPERLINK("'+item["videolink"]+'";"'+item["title"]+'")' # 設定超連結 sheet.col(0).width = int(256 * len(title_data) * 3/5) # 設定列寬 sheet.write(i,xlwt.Formula(title_data),xstyle) name_data = 'HYPERLINK("'+item["uplink"]+'";"'+item["upname"]+'")' sheet.col(1).width = int(256 * len(name_data) * 3/5) sheet.write(i,1,xlwt.Formula(name_data),xstyle) sheet.write(i,2,item["rank"],3,item["hot"],4,item["play"],5,item["comment"],xstyle) i += 1 # 如果檔案存在,則將其刪除 file = "b站熱門視訊資訊.xls" if os.path.exists(file): os.remove(file) workbook.save(file) if __name__ == '__main__': write_Excel()
結果展示:
以上就是本文的全部內容,希望對大家的學習有所幫助,也希望大家多多支援我們。