猫眼爬虫->电影名称,购票地址,电影图片，以及评分

最新推荐文章于 2020-12-11 23:16:31 发布

藏锋于鞘

最新推荐文章于 2020-12-11 23:16:31 发布

阅读量813

点赞数

分类专栏： pyhton

本文链接：https://blog.csdn.net/qq_38632611/article/details/86649524

版权

pyhton 专栏收录该内容

7 篇文章 3 订阅

订阅专栏

猫眼爬取网站为: https://maoyan.com/films

在这里插入图片描述
该网页中相关记录存放在
result.txt

会在本地创建一个photo的文件夹里面是网页中，电影名称和电影图片
在这里插入图片描述

import json
import requests
from requests.exceptions import RequestException
import re
import os

def get_one_page(url):
    try:
        response = requests.get(url)
        if response.status_code == 200:
            return response.text
        return None
    except RequestException:
        return None

def ping_fen(item):
    if 'integer' in item:
        return item.strip()[19:21] + item.strip()[45:46]
    else:
        return item

def parse_one_page(html,url):
    pattern = re.compile('<dd>.*?movie-item.*?a.*?="(.*?)" target.*?poster-default.*?img.*?="(.*?)" />.*?movie-item-title.*?a.*?>(.*?)</a>.*?channel-detail-orange.*?>(.*?)</div>', re.S)
    items = re.findall(pattern, html)
    for item in items:
        yield {
            '购票地址': url + item[0],
            '电影图片': item[1],
            '电影名称': item[2],
            '评分': ping_fen(item[3])
        }

def write_to_file(content):
    with open('result.txt', 'a', encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False) + '\n')

def DeatleFile(file_name):
    path = os.getcwd() + '\\' + file_name
    for i in os.listdir(os.getcwd()):
        if file_name in i:
            for ii in os.listdir(path):
                os.remove(path + '\\' + ii)
            os.removedirs(path)

def CreatFile(file_nam):
    os.makedirs(os.getcwd() + '\\' + file_nam)

def ReadFile(file_name):
    fo = open(file_name, "r+",encoding='UTF-8')
    lines = fo.readlines()
    photo_list = []
    for line in lines:
        pattern = re.compile('电影图片.*? "(.*?)".*?电影名称".*?"(.*?)"',re.S)
        listA = re.findall(pattern, line)
        if listA != None:
            photo_list.append(listA)
    return photo_list

def DownPhoto(list_html,file_name):
    for photo_httml in list_html:
        for messgae in photo_httml:
            r = requests.get(messgae[0])
            with open(os.getcwd() + '/' + file_name + '/' + str(messgae[1]) + '.png', 'wb') as f:
                f.write(r.content)
                f.close()


def Creat_Photo(file_name):
    DeatleFile(file_name)
    CreatFile(file_name)
    listA = ReadFile('result.txt')
    DownPhoto(listA, file_name)

def main():
    url = 'https://maoyan.com'
    html = get_one_page(url + '/films')
    for item in parse_one_page(html, url):
        write_to_file(item)

if __name__ == '__main__':
    main()
    Creat_Photo('photo')