爬取热门电影

爬取热门电影实战

参考书籍：python程序设计
安装的库：
pip install bs4
如果下载的较慢可以加入网址
pip install -i https://pypi.tuna.tsinghua.edu.cn/simple bs4

#  爬取2345网站电影排行前50的电影信息
import requests
from bs4 import BeautifulSoup
def getHtml(url):
    try:
        r=requests.get(url,timeout=30)
        r.raise_for_status()
        r.encoding='gbk'
        return r.text
    except:
        return ''
    pass
def saveInfo(html):
    soup=BeautifulSoup(html,'html.parser')
    move_ls=soup.find('ul',class_='picList clearfix')
    movies=move_ls.find_all('li')
    for top in movies:
        img_url=top.find('img')['src']   # 查找所有图片链接
        name=top.find('span',class_='sTit').get_text()  #得到电影名称
        try:
            time=top.find('span',class_='sIntro').get_text()
            pass
        except:
            time='暂时无上映时间信息'
            pass
        try:
            actors=top.find('p',class_='pActor')
            actor=''
            for act in actors.contents:
                actor=actor+act.string+''
                pass
            pass
        except:
            actor='暂时无演员姓名'
            pass
        
        if top.find('p',class_='pTxt pIntroHide'):
            intro=top.find('p',class_='pTxt pIntroHide').get_text()
            pass
        else:
            intro=top.find('p',class_='pTxt pIntroShow').get_text()
            pass
        print('影片名:   {}\t{}\n{}\n{}\n\n'.format(name,time,actor,intro))
        # 下载图片
        with open('E:/下载/sp/'+name+'.jpg','wb+')as f:
            img_url="http:"+img_url
            imgdata=requests.get(img_url).content
            f.write(imgdata)
            pass
        pass
    pass
def main():
    url="https://dianying.2345.com/top/"
    html=getHtml(url)
    saveInfo(html)
    pass
main()

运行结果;
等50个电影信息