Python爬虫1：批量获取电影标题和剧照

1.爬取某电影网站的电影名称

下面展示一些 代码。

import requests
from lxml import etree

def dianying(number):
    url ='https://www.piaku.cc/p/DY-'+str(number)+'/'
    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36"
    }
    response = requests.get(url, headers=headers)
    # print(response)#打印是否200
    html = etree.HTML(response.text)
    name = html.xpath('//div[@class="li-bottom"]/h3/a/text()')
    for i in name:
        print('正在下载：' + i)
        with open('d.xlsx', 'a+', encoding='utf-8') as f:
                f.write(i + '\n')

for i in range(1,21):
    dianying(i)
    print('------------------------第'+str(i)+'页下载完成------------------------')

下面展示一些 效果图。

2.批量获取多个页面的电影照片

下面展示一些 代码。

import os
import re
from time import sleep

import requests
from lxml import etree
def piaku_photo(number):
    url = 'https://www.piaku.cc/p/DY-'+str(number)+'/'
    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36"
    }
    response = requests.get(url, headers=headers)
    # print(response)
    html = etree.HTML(response.text)
    name = html.xpath('//div[@class="li-img"]/a/img/@alt')
    photo = html.xpath('//div[@class="li-img"]/a/img/@src')
    photos = []
    names = []
    #返回的图片链接有些不存在，需要重新处理一下
    for i, z in zip(photo, name):
        if i[0:4] == 'http':
            photos.append(i)
            names.append(z)
    path = '片库照片'
    #创建文件夹，判断是否存在
    if not os.path.exists(path):
        os.mkdir(path)
    #下载图片
    for i, a in zip(names, photos):
        name1 = i + '.jpg'
        photoaddress = requests.get(a)
        with open(path + '/' + name1, 'wb') as f:
            sleep(0.5)
            f.write(photoaddress.content)
        print(i + ":" + a + '----------下载成功')
#批量下载多个页面
for i in range(1,3):
    piaku_photo(i)
    print('------------------------第'+str(i)+'页下载完成------------------------')

最终效果展示：