from bs4 import BeautifulSoup # 解析網(wǎng)頁
import re# 正則表達(dá)式，進(jìn)行文字匹配
import urllib.request,urllib.error  # 通過瀏覽器請求數(shù)據(jù)
import sqlite3  # 輕型數(shù)據(jù)庫
import time  # 獲取當(dāng)前時(shí)間

def main():
	#聲明爬取網(wǎng)站
 baseurl = "https://www.bilibili.com/v/popular/rank/all"
 #爬取網(wǎng)頁
 datalist = getData(baseurl)
 # print(datalist)
 #保存數(shù)據(jù)
 dbname = time.strftime("%Y-%m-%d", time.localtime())
 dbpath = "BiliBiliTop100  " + dbname
 saveData(datalist,dbpath)

from bs4 import BeautifulSoup #解析網(wǎng)頁
import re # 正則表達(dá)式，進(jìn)行文字匹配
import urllib.request,urllib.error
import sqlite3
import time

def main():
 #聲明爬取網(wǎng)站
 baseurl = "https://www.bilibili.com/v/popular/rank/all"
 #爬取網(wǎng)頁
 datalist = getData(baseurl)
 # print(datalist)
 #保存數(shù)據(jù)
 dbname = time.strftime("%Y-%m-%d", time.localtime())
 dbpath = "BiliBiliTop100  " + dbname
 saveData(datalist,dbpath)
#re正則表達(dá)式
findLink =re.compile(r'<a class="title" href="(.*?)" rel="external nofollow" ') #視頻鏈接
findOrder = re.compile(r'<div class="num">(.*?)</div>') #榜單次序
findTitle = re.compile(r'<a class="title" href=".*?" rel="external nofollow"  rel="external nofollow"  target="_blank">(.*?)</a>') #視頻標(biāo)題
findPlay = re.compile(r'<span class="data-box"><i class="b-icon play"></i>([\s\S]*)(.*?)</span> <span class="data-box">') #視頻播放量
findView = re.compile(r'<span class="data-box"><i class="b-icon view"></i>([\s\S]*)(.*?)</span> <a href=".*?" rel="external nofollow"  rel="external nofollow"  target="_blank"><span class="data-box up-name">') # 視頻評(píng)價(jià)數(shù)
findName = re.compile(r'<i class="b-icon author"></i>(.*?)</span></a>',re.S) #視頻作者
findScore = re.compile(r'<div class="pts"><div>(.*?)</div>綜合得分',re.S) #視頻得分
def getData(baseurl):
 datalist = []
 html = askURL(baseurl)
 #print(html)
 soup = BeautifulSoup(html,'html.parser')  #解釋器
 for item in soup.find_all('li',class_="rank-item"):
  # print(item)
  data = []
  item = str(item)
  Order = re.findall(findOrder,item)[0]
  data.append(Order)
  # print(Order)
  Link = re.findall(findLink,item)[0]
  Link = 'https:' + Link
  data.append(Link)
  # print(Link)
  Title = re.findall(findTitle,item)[0]
  data.append(Title)
  # print(Title)
  Play = re.findall(findPlay,item)[0][0]
  Play = Play.replace(" ","")
  Play = Play.replace("\n","")
  Play = Play.replace(".","")
  Play = Play.replace("萬","0000")
  data.append(Play)
  # print(Play)
  View = re.findall(findView,item)[0][0]
  View = View.replace(" ","")
  View = View.replace("\n","")
  View = View.replace(".","")
  View = View.replace("萬","0000")
  data.append(View)
  # print(View)
  Name = re.findall(findName,item)[0]
  Name = Name.replace(" ","")
  Name = Name.replace("\n","")
  data.append(Name)
  # print(Name)
  Score = re.findall(findScore,item)[0]
  data.append(Score)
  # print(Score)
  datalist.append(data)
 return datalist
def askURL(url):
 #設(shè)置請求頭
 head = {
  "User-Agent": "Mozilla/5.0 (Windows NT 10.0;Win64;x64) AppleWebKit/537.36(KHTML, likeGecko) Chrome/80.0.3987.163Safari/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,dbpath):
 init_db(dbpath)
 conn = sqlite3.connect(dbpath)
 cur = conn.cursor()
 for data in datalist:
  sql = '''
  insert into Top100(
  id,info_link,title,play,view,name,score)
  values("%s","%s","%s","%s","%s","%s","%s")'''%(data[0],data[1],data[2],data[3],data[4],data[5],data[6])
  print(sql)
  cur.execute(sql)
  conn.commit()
 cur.close()
 conn.close()
def init_db(dbpath):
 sql = '''
 create table Top100
 (
 id integer primary key autoincrement,
 info_link text,
 title text,
 play numeric,
 view numeric,
 name text,
 score numeric
 )
 '''
 conn = sqlite3.connect(dbpath)
 cursor = conn.cursor()
 cursor.execute(sql)
 conn.commit()
 conn.close()

if __name__ =="__main__":
 main()