B站热门信息爬取

寒假爬虫练习，之前做过豆瓣TOP250，出于练手考虑我决定对原代码进行修改爬取B站2月3日的热门视频
https://www.bilibili.com/v/popular/rank/all

# -*- coding: utf-8 -*-
# @Time : 2021/2/2 17:08
# @Author : 楠缘
# @Email : 2251354955@163.com
# @Software: pycharm
# @Blog ：https://blog.csdn.net/m0_51586991
from bs4 import BeautifulSoup
import re
import urllib.request,urllib.error
import xlwt
import sqlite3
findlink = re.compile('<a href="//(.*?)"')
findtitle = re.compile('<a class="title" href=".*_blank">(.*)</a>')
findrating = re.compile(r'<div class="detail">.*?<i class="b-icon play"></i>\n              (.*?)\n            </span>',re.S)#播放量
findview = re.compile(r'<span class="data-box"><i class="b-icon view"></i>\n              (.*?)\n            </span>',re.S)
findplay = re.compile(r'<span class="data-box up-name"><i class="b-icon author"></i>\n                (.*?)\n              </span>',re.S)
findwww = re.compile(r'<div class="pts"><div>(.*)</div>')

def main():
    baseurl = "https://www.bilibili.com/v/popular/rank/all"
    datalist = getData(baseurl)
    savepath = "B站热门2月3日.xls"
    saveData(datalist,savepath)


def getData(baseurl):
    datalist = []
    for i in range(0,1):
        url = baseurl
        html = askURL(url)      #保存获取到的网页源码
        soup = BeautifulSoup(html,"html.parser")
        for content in soup.find_all('div',class_="content"):     #查找符合要求的字符串
            # print(content)
            # break
            data = []#保存一部视频的所有信息
            content = str(content)
            link = re.findall(findlink,content)[0]
            data.append(link)
            title = re.findall(findtitle,content)
            data.append(title)
            rating = re.findall(findrating,content)
            data.append(rating)
            view = re.findall(findview,content)
            data.append(view)
            play = re.findall(findplay,content)
            data.append(play)
            www = re.findall(findwww,content)
            data.append(www)
            datalist.append(data)
    print(datalist)
    return datalist


def askURL(url):
    head = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36"}
    request = urllib.request.Request(url,headers=head)
    html = ""
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8")
        # print(html)
    except urllib.error.URLError as e:
        if hasattr(e,"code"):
            print(e.code)
        if hasattr(e,"reason"):
            print(e.reason)
    return html


def saveData(datalist,savepath):
    book = xlwt.Workbook(encoding="utf-8")
    sheet = book.add_sheet('B站热门2月3日.xls',cell_overwrite_ok=True)
    col = ("视频链接","视频名称","播放量","弹幕量","作者","热度")
    for i in range(0,6):
        sheet.write(0,i,col[i])
    for i in range(0,100):
        print("第%d条"%i)
        data = datalist[i]
        for j in range(0,6):
            sheet.write(i+1,j,data[j])
    book.save("B站热门2月3日.xls")


if __name__ == '__main__':
    main()
    print('爬取完毕')

这次的代码在编写时遇到不少麻烦，一些问题导致代码看起来很乱，例如18，19，20行存在的大量空格就是一个我现在没有能够解决的问题，如果哪位大佬可以出手帮助将十分感谢。