用Python抓取大衆點評的用戶評論

大衆點評的知识产权声明可真是霸道啊！還是自己先保存一份。下面代碼先將評論及商戶保存到sqlite數據庫，如果需要還可以導出成CSV，這樣辦公軟件就能直接打開查看了。

from bs4 import BeautifulSoup
import sys,time,random,urllib,http.cookiejar,socket,sqlite3,csv


goOn=1
stopDate=''
UserID=''
review={'shopName':'','shopAddr':'','shopURL':'','reviewURL':'','star':'',
'starDetail':'','costPerPeople':'','reviewText':'','dishes':'','reviewTime':''}

def getHTML(url):
  print("Fetching "+url)
  request = urllib.request.Request(url)
  request.add_header("User-Agent", "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:37.0) Gecko/20100101 Firefox/37.0")
  try:
    response = urllib.request.urlopen(request)
  except (urllib.error.HTTPError, socket.error,urllib.error.URLError) as e:
    print('Connection error occurred when inserting data.'+str(e))
  else:
    if response.code != 200:
      print("Error code:"+response.code)  
    else:
      html = response.read().decode('utf-8')
      return html

def getList(url):
  global review,goOn
  reviewList=getHTML(url)
  soupAll = BeautifulSoup(reviewList).find_all("div",{"class":"txt J_rptlist"})

  for soup in soupAll:
    shopLink = soup.find("a",{"class":"J_rpttitle"})
    review['shopName']=shopLink.text
    review['shopURL']=shopLink.get("href")
    
    shopAddr = soup.find("p",{"class":"col-exp"})
    review['shopAddr']=shopAddr.text
    
    reviewID = soup.find("a",{"class":"J_flower aheart"})
    review['reviewURL']="http://www.dianping.com/review/"+reviewID.get("data-id")
    
    reviewDateDiv = soup.find("div",{"class":"mode-tc info"})
    reviewDateSpan=reviewDateDiv.find("span",{"class":"col-exp"})
    reviewDate=str(reviewDateSpan.text)[3:]
    if(len(reviewDate)==8 and reviewDate>stopDate):
      getReview(review['reviewURL'])
      #抓取頻率
      time.sleep(random.randrange(5,10))
    else:
      goOn=0
  if(goOn==0):
    print("Finished.")
    exit()
    
      
    

def save():
  global review,UserID
  conn = sqlite3.connect('DZDB_'+UserID+'_Reviews.db')
  c = conn.cursor()
  c.execute("""create table if not exists reviews (ID integer primary key not NULL,shopName char(50),shopAddr char(100),shopURL char(100),reviewURL char(100),star char(1),starDetail char(15),costPerPeople char(15),reviewText TEXT,dishes char(100),reviewTime char(20))""")
  s="""insert into reviews (ID,shopName,shopAddr,shopURL,reviewURL,star,starDetail,costPerPeople,reviewText,dishes,reviewTime) VALUES (NULL,\'"""+review['shopName']+'\',\''+review['shopAddr']+'\',\''+review['shopURL']+'\',\''+review['reviewURL']+'\',\''+str(review['star'])+'\',\''+review['starDetail']+'\',\''+review['costPerPeople']+'\',\''+review['reviewText']+'\',\''+review['dishes']+'\',\''+review['reviewTime']+'\')'
  c.execute(s)
  conn.commit()
  c.close
  print("Record at "+review['shopName']+" saved to Datebase.")
  review={'shopName':'','shopAddr':'','shopURL':'','reviewURL':'','star':'',
'starDetail':'','costPerPeople':'','reviewText':'','dishes':'','reviewTime':''}

def getReview(url):
  global review
  reviewHTML=getHTML(url)
  reviewAll=BeautifulSoup(reviewHTML)
  shopInfo= reviewAll.find("ul",{"class":"contList-info"})
  star=str(shopInfo.find("li"))
  if("msstar50" in star):
    review['star']=5
  elif ("msstar40" in star):
    review['star']=4
  elif ("msstar30" in star):
    review['star']=3
  elif ("msstar20" in star):
    review['star']=2
  elif ("msstar10" in star):
    review['star']=1
  else:
    review['star']=0
  starDetails=shopInfo.find_all("span",{"class":"rst"})
  starDetail=""
  for s in starDetails:
    s1=s.text[0:3]
    starDetail=starDetail+s1
  review['starDetail']=starDetail
  
  reviewText= reviewAll.find("div",{"class":"contList-con"})
  review['reviewText']=reviewText.text
  units= reviewAll.find_all("div",{"class":"comment-unit"})
  for unit in units:
    unit=str(unit.text).replace('\n','')
    if("人均:" in unit):    
      review['costPerPeople']=unit[4:]
    elif("喜欢的菜:" in unit): 
      unit=unit.replace(' ','')
      unit=unit.replace('\xa0',' ')
      review['dishes']=unit[7:]
    
  reviewInfo= reviewAll.find("ul",{"class":"contList-fn"})  
  reviewTime=reviewInfo.find("li")
  review['reviewTime']=reviewTime.text
  save() 

def main():
  fun=int(input("请输入数字选择功能：\n[1]抓取数据，[2]导出数据： \n"))
  if(fun==1):
    fetchReview()
  elif(fun==2):
    sqliteToCSV()
  else:
    print("请输入1或2。")

    
def sqliteToCSV():
  dbFile=str(input("请输入数据库文件名:\n"))
  with open(dbFile+'.csv','w+',newline='') as csvfile:
    spamwriter = csv.writer(csvfile)
    conn=sqlite3.connect(dbFile)
    c = conn.cursor()
    spamwriter.writerow(['ID','shopName','shopAddr','shopURL','reviewURL','star',
'starDetail','costPerPeople','reviewText','dishes','reviewTime'])
    for row in c.execute('SELECT * FROM reviews'):
      spamwriter.writerow(row)
    c.close()
    print("CSV文件成功導出。")
    
def fetchReview():
  #抓取参数：用户ID，起始页，结束日期
  global stopDate,UserID
  UserID=str(input("请输入您的大众点评ID，可以在您大众点评主页的网址中看到，如23262500：\n"))
  startPageNo=int(input("开始的页码，如1:\n"))
  stopDate=str(input("请输入评论结束日期(yy-mm-dd)，如00-00-00:\n"))
  
  urlBase="http://www.dianping.com/member/"+UserID+"/reviews?pg="
  startPageNo=startPageNo-1
  while(goOn==1):
    startPageNo=startPageNo+1
    getList(urlBase+str(startPageNo))
    
if __name__ == "__main__":
    main()

幾點說明

• 抓取頻率不要過大，否則大衆點評會屏蔽IP。我在抓取到20頁左右的時候碰到過一次屏蔽IP。如果意外中斷，你可以設置參數繼續下載，附w3school的SQL基礎教程。
• BeautifulSoup真是個好工具，連Qpython3都自帶了，但是遺憾的是這個代碼在Qpython3上跑報NoneType錯誤。
• 我用了幾次都沒問題。