Fork me on GitHub

Pycharm安装Bitbucket git 管理工具及猫眼排名100电影简单的爬虫抓取

File-----〉setting ------〉Plugins 搜索 Bitbucket Linky 

下载安装完成后重启Pycharm,选中项目右点 将会看见git菜单

 

 

 

 

import  requests
from bs4 import BeautifulSoup




def get_one_page(url):
    try:
        session =requests.Session()
        headers={"User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) "
                              "AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.170 Safari/537.36"}
        proxy = {
            'http': 'xxxxxxxxxxxxx',
            'Login':'xxxx\Lxxx',
            'Password':'xxxx.'
        }
        response=session.get(url,headers=headers,verify=False,proxies = proxy,timeout = 20)
        # print('gee_one_page' +response.text)
        print(response.status_code)
        if response.status_code==200:
            return response.text
        return None
    except Exception as e :
        print(e)
        return None

def parse_page(html):
    try:
        soup=BeautifulSoup(html,'lxml')
        for dd in soup.find_all('dd'):
            index=dd.find('i').text
            title=dd.select('div>div>div>p>a')[0].text
            actors=dd.select('div>div>div>p')[1].text[20:-9]
            time=dd.select('div>div>div>p')[2].text[5:]
            print('排名:%s,电影名称:%S,主演:%s,上映时间:%s' %(index,title,actors,time))
    except Exception as e:
        print(e)
        return None


def main():
    for offset in range(0,100,10):
        url = "http://maoyan.com/board/4?offset="+str(offset)
        html=get_one_page(url)
        parse_page(html)

main()

 

posted @ 2018-05-25 16:38  低调的神  阅读(334)  评论(0编辑  收藏  举报