爬取貓眼TOP100的電影信息 urllib+mongdb

import pymongo
import time
import urllib.request
import re

print("開始")
#鏈接數據庫
client=pymongo.MongoClient(host='localhost',port=27017)
db=client.test
collection=db.maoyan

#獲取html頁面內容
def gethtml(url):
    time.sleep(2)
    response=urllib.request.urlopen(url)
    html=response.read().decode('utf-8')
    if response.status==200:
        return html
    else:
        return None

#正則表達式解析html頁面內容並放入mongodb數據庫
def getContent(html):
    pattern=re.compile( '<dd>.*?board-index.*?>(.*?)</i>.*?data-src="(.*?)".*?name.*?a.*?>(.*?)</a>.*?star.*?>(.*?)</p>.*?releasetime.*?>(.*?)</p>.*?integer.*?>(.*?)</i>.*?fraction.*?>(.*?)</i>.*?</dd>',
        re.S)
    items=re.findall(pattern,html)
    for item in items:
        yild={
            'index': item[0],
            'image': item[1],
            'title': item[2].strip(),
            'actor': item[3].strip()[3:] if len(item[3]) > 3 else '',
            'time': item[4].strip()[5:] if len(item[4]) > 5 else '',
            'score': item[5].strip() + item[6].strip()
        }
        collection.insert(yild)

#"將url放入mongodb中"


url="http://maoyan.com/board/4?offset="
list=[]
result=[]
for i in range(6,10):
    html=gethtml(url+str(i*10))
    getContent(html)
print("結束")