猫眼电影top100海报爬取和生成照片墙

本文来源吾爱破解论坛

话不多说先上结果


最后生成的照片墙

1.png (987.38 KB, 下载次数: 1)

下载附件  保存到相册

2019-8-20 16:55 上传

import requests
from bs4 import BeautifulSoup
import re
import time
import os
import math
import pickle
from PIL import Image

#存图片的路径
path = 'result/'

headers={
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36'
}

#请求返回网页源码
def get_html(url):
    response = requests.get(url,headers=headers)
    if response.status_code ==200:
        return response.text
    else:
        print('请求网页失败')

#解析网页源码得到影片title和海报src
def parse(html):
    soup = BeautifulSoup(html,'lxml')
    dl = soup.select('#app > div > div > div.main > dl')[0]
    dds = dl('dd')
    for dd in dds:
        title = dd.find('a')['title']
        star = dd.select('.star')[0].string.strip()
        img = dd.select('img.board-img')[0]['data-src']
        yield {
            'title':title,
            'star':star,
            'img':img
        }

#路径检测
def make_dir(path):
    if not os.path.exists(path):
        os.makedirs(path)

#下载影片海报至result文件夹
def downlord_img(title,img_src):
    make_dir(path)
    match = re.search('(https.*?jpg)',img_src,re.S)
    if match:
        src = match.group(1)
        response = requests.get(src,headers=headers)
        if response.status_code ==200:
            with open(os.path.join(path,title+'.jpg'),'ab') as f:
                f.write(response.content)
                f.close()

#这段代码作者@Charles
#指定文件夹内图片生成图片墙
def makePicturesWall(picdir):
    picslist = os.listdir(picdir)
    num_pics = len(picslist)
    size = 128
    line_numpics = int(math.sqrt(num_pics))
    picwall = Image.new('RGBA', (line_numpics*size, line_numpics*size))
    x = 0
    y = 0
    for pic in picslist:
        img = Image.open(os.path.join(picdir, pic))
        img = img.resize((size, size), Image.ANTIALIAS)
        picwall.paste(img, (x*size, y*size))
        x += 1
        if x == line_numpics:
            x = 0
            y += 1
    print('图片墙制作成功！')
    picwall.save("picwall.png")

def main():
    count = 0
    for i in range(0,10):
        print('准备下载第{}页'.format(str(i+1)))
        url = 'https://maoyan.com/board/4?offset={}'.format(str(i*10))
        html = get_html(url)
        data = parse(html)
        for each in data:
            count+=1
            downlord_img(each['title'],each['img'])
            print('下载{}海报成功'.format(each['title']))
        print('准备睡眠3s')
        time.sleep(3)
    makePicturesWall(path)

if __name__ == '__main__':
    main()

top100.PNG (590.19 KB, 下载次数: 1)

下载附件  保存到相册

2019-8-20 16:57 上传

下载的100张海报图片