spider - 猫眼电影top100

一、获取网页

import requests

# 获取网页
def get_page():
    # 请求头（有些反扒机制需要检测）
    headers = {
        "User-Agent": "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)"
    }

    
    url = 'https://maoyan.com/board/4'
    response = requests.get(url，headers=headers)
    if response.status_code == 200:
        return response.content.decode('utf-8')
    return None

def main():
    html = get_page()
    print(html)

    
if __name__ == '__main__':
    main()

解析网页

• 在main()上面再定义一个parse_page()

import requests
import re

# 获取网页
def get_page():
    # 请求头（有些反扒机制需要检测）
    headers = {
        "User-Agent": "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)"
    }

    
    url = 'https://maoyan.com/board/4'
    response = requests.get(url)
    if response.status_code == 200:
        return response.content.decode('utf-8')
    return None

# 解析网页
def parse_page(html):
    # 片名
    pattern = re.compile('movieId.*?>.*?<img.*?<img.*?alt="(.*?)" class.*?', re.S)
    movie_names = re.findall(pattern, html)
    print('片名：',movie_names)

    # 主演
    pattern = re.compile('<p class="star">(.*?)</p>', re.S)
    actors = re.findall(pattern,html)
    # 去字符串前后空格
    actors = [actor.strip() for actor in actors]
    print('主演：',actors)

    # 上映时间
    pattern = re.compile('<p class="releasetime">(.*?)</p>', re.S)
    time = re.findall(pattern, html)
    time = [i.strip() for i in time]
    print('上映时间：',time)

    # 封面图片
    pattern = re.compile('movieId.*?>.*?<img.*?<img.*?data-src="(.*?)" alt.*?', re.S)
    img = re.findall(pattern, html)
    print('封面图片：',img)

    # 排名
    pattern = re.compile('<i class="board-index board-index-(.*?)">.*?</i>', re.S)
    rank = re.findall(pattern, html)
    print('排名：',rank)

    # 评分
    pattern = re.compile('<p class="score"><i class="integer">(.*?)</i><i class="fraction">(.*?)</i></p>', re.S)
    score = re.findall(pattern, html)
    score = [''.join(i) for i in score]
    print('评分：', score)


    # 链接
    pattern = re.compile('<div class="movie-item-info">.*?<p class="name"><a href="(.*?)" title', re.S)
    detail = re.findall(pattern, html)
    detail = [i.strip() for i in detail]
    print('链接：', detail)


def main():
    html = get_page()
#     print(html)
    parse_page(html)

    
if __name__ == '__main__':
    main()

# 打印的内容
>>>>
片名： ['霸王别姬', '肖申克的救赎', '罗马假日', '这个杀手不太冷', '泰坦尼克号', '教父', '唐伯虎点秋香', '千与千寻', '魂断蓝桥', '乱世佳人']
主演： ['主演：张国荣,张丰毅,巩俐', '主演：蒂姆·罗宾斯,摩根·弗里曼,鲍勃·冈顿', '主演：格利高里·派克,奥黛丽·赫本,埃迪·艾伯特', '主演：让·雷诺,加里·奥德曼,娜塔莉·波特曼', '主演：莱昂纳多·迪卡普里奥,凯特·温丝莱特,比利·赞恩', '主演：马龙·白兰度,阿尔·帕西诺,詹姆斯·肯恩', '主演：周星驰,巩俐,郑佩佩', '主演：柊瑠美,入野*,夏木真理', '主演：费雯·丽,罗伯特·泰勒,露塞尔·沃特森', '主演：费雯·丽,克拉克·盖博,奥利维娅·德哈维兰']
上映时间： ['上映时间：1993-01-01', '上映时间：1994-10-14(美国)', '上映时间：1953-09-02(美国)', '上映时间：1994-09-14(法国)', '上映时间：1998-04-03', '上映时间：1972-03-24(美国)', '上映时间：1993-07-01(中国香港)', '上映时间：2001-07-20(日本)', '上映时间：1940-05-17(美国)', '上映时间：1939-12-15(美国)']
封面图片： ['https://p1.meituan.net/movie/[email protected]_220h_1e_1c', 'https://p0.meituan.net/movie/[email protected]_220h_1e_1c', 'https://p0.meituan.net/movie/[email protected]_220h_1e_1c', 'https://p0.meituan.net/movie/[email protected]_220h_1e_1c', 'https://p1.meituan.net/movie/[email protected]_220h_1e_1c', 'https://p1.meituan.net/movie/[email protected]_220h_1e_1c', 'https://p0.meituan.net/movie/[email protected]_220h_1e_1c', 'https://p0.meituan.net/movie/[email protected]_220h_1e_1c', 'https://p0.meituan.net/movie/[email protected]_220h_1e_1c', 'https://p0.meituan.net/movie/[email protected]_220h_1e_1c']
排名： ['1', '2', '3', '4', '5', '6', '7', '8', '9', '10']
评分： ['9.6', '9.5', '9.1', '9.5', '9.6', '9.3', '9.2', '9.3', '9.2', '9.1']
链接： ['/films/1203', '/films/1297', '/films/2641', '/films/4055', '/films/267', '/films/1247', '/films/837', '/films/1212', '/films/2760', '/films/7431']

下面附完整代码（将爬取到的内容存到本地）

import json
import re

import requests


# 获取网页
def get_page(page):
    # 请求头
    headers = {
        "User-Agent": "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)"
    }

    url = 'https://maoyan.com/board/4?offset='+str(page)
    # url = 'https://maoyan.com/board/4'
    response = requests.get(url)
    if response.status_code == 200:
        return response.content.decode('utf-8')
    return None

# 获取所有 网页
def get_all_pages():
    result = []
    for i in range(10):
        page = i*10
        html = get_page(page)
        result_list = parse_page(html)
        result.append(result_list)

    return result

# 写入图片
def save_img(cover_url):
    response = requests.get(cover_url)
    filename = cover_url.split('/')[-1].split('@')[0]

    with open('./images/%s' % filename,'wb')as f:
        f.write(response.content)

# 解析网页
def parse_page(html):
    # 片名
    pattern = re.compile('movieId.*?>.*?<img.*?<img.*?alt="(.*?)" class.*?', re.S)
    movie_names = re.findall(pattern, html)
    # print('片名：',movie_names)

    # 主演
    pattern = re.compile('<p class="star">(.*?)</p>', re.S)
    actors = re.findall(pattern,html)
    # 去字符串前后空格
    actors = [actor.strip() for actor in actors]
    # print('主演：',actors)

    # 上映时间
    pattern = re.compile('<p class="releasetime">(.*?)</p>', re.S)
    time = re.findall(pattern, html)
    time = [i.strip() for i in time]
    # print('上映时间：',time)

    # 封面图片
    pattern = re.compile('movieId.*?>.*?<img.*?<img.*?data-src="(.*?)" alt.*?', re.S)
    img = re.findall(pattern, html)

    # print('封面图片：',img)

    # 排名
    pattern = re.compile('<i class="board-index board-index-(.*?)">.*?</i>', re.S)
    rank = re.findall(pattern, html)
    # print('排名：',rank)

    # 评分
    # '<p class="score"><i class="integer">(.*?)</i><i class="fraction">(.*?)</i></p>'
    pattern = re.compile('<p class="score"><i class="integer">(.*?)</i><i class="fraction">(.*?)</i></p>', re.S)
    score = re.findall(pattern, html)
    score = [''.join(i) for i in score]
    # print('评分：', score)


    # 链接
    # '<div class="movie-item-info">.*?<p class="name"><a href="(.*?)" title'
    pattern = re.compile('<div class="movie-item-info">.*?<p class="name"><a href="(.*?)" title', re.S)
    detail = re.findall(pattern, html)
    detail = [i.strip() for i in detail]
    # print('链接：', detail)

    print('spider...')

    # 组装json
    result_list = []

    for i in range(len(movie_names)):
        result_dict = {}
        result_dict['movie_name'] = movie_names[i]
        result_dict['actor'] = actors[i]
        result_dict['time'] = time[i]
        result_dict['img'] = img[i]
        # 保存图片到本地
        save_img(result_dict['img'])
        result_dict['rank'] = rank[i]
        result_dict['score'] = score[i]
        result_dict['detail'] = detail[i]
        result_list.append(result_dict)

    return result_list


def save_json_file(result):
    json_str = json.dumps(result, ensure_ascii=False)
    with open('maoyan.json','w', encoding='utf-8')as f:
        f.write(json_str)


def main():
    # html = get_page()

    # print(html)
    # parse_page(html)
    result = get_all_pages()
    print(result)
    save_json_file(result)


if __name__ == '__main__':
    main()

转载于:https://www.jianshu.com/p/7eadd87368b2