Requests+正则表达式爬取猫眼电影(TOP100榜)

猫眼电影网址:www.maoyan.com

前言:网上一些大神已经对猫眼电影进行过爬取,所用的方法也是各有其优,最终目的是把影片排名、图片、名称、主要演员、上映时间与评分提取出来并保存到文件或者数据库,本人也是巩固知识进行练习,整理笔记方便阅读

 

 

获取单个网页

 # 获取单个网页html
    def get_one_page(self,url):
        try:
            response =requests.get(url)
            if response.status_code==200:
                return response.text
            return None
        except RequestException:
            return None

 

利用正则表达式解析网页

def pare_one_page(self,html):
    pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)"'
                         '.*?name"><a.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)'
                         '</p>.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>',re.S)
    items = re.findall(pattern,html)
    for item in items:
        yield {
            # 索引
            'index':item[0],
            # 封面
            'image':item[1],
            # 电影名称
            'name': item[2],
            # 演员
            'actor': item[3].strip()[3:],
            # 上映时间
            'time': item[4].strip()[5:],
            # 评分
            'score': item[5]+item[6]
        }

 

写入文件

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

 

执行写入,打印到控制台

# 猫眼电影TOP榜url拼接
url = 'https://maoyan.com/board/4?offset='+str(offset)
html = self.get_one_page(url)
for item in self.pare_one_page(html):
    self.write_to_file(item)
    print(item)

 

循环10页

if __name__ == '__main__':
   m = maoyan()
   for i in range(10):
       m.main(i*10)

 




猫眼电影7-22日的数据

{"index": "1", "image": "https://p1.meituan.net/movie/20803f59291c47e1e116c11963ce019e68711.jpg@160w_220h_1e_1c", "name": "霸王别姬", "actor": "张国荣,张丰毅,巩俐", "time": "1993-01-01", "score": "9.5"}
{"index": "2", "image": "https://p0.meituan.net/movie/283292171619cdfd5b240c8fd093f1eb255670.jpg@160w_220h_1e_1c", "name": "肖申克的救赎", "actor": "蒂姆·罗宾斯,摩根·弗里曼,鲍勃·冈顿", "time": "1994-09-10(加拿大)", "score": "9.5"}
{"index": "3", "image": "https://p0.meituan.net/movie/289f98ceaa8a0ae737d3dc01cd05ab052213631.jpg@160w_220h_1e_1c", "name": "罗马假日", "actor": "格利高里·派克,奥黛丽·赫本,埃迪·艾伯特", "time": "1953-09-02(美国)", "score": "9.1"}
{"index": "4", "image": "https://p1.meituan.net/movie/6bea9af4524dfbd0b668eaa7e187c3df767253.jpg@160w_220h_1e_1c", "name": "这个杀手不太冷", "actor": "让·雷诺,加里·奥德曼,娜塔莉·波特曼", "time": "1994-09-14(法国)", "score": "9.5"}
{"index": "5", "image": "https://p1.meituan.net/movie/b607fba7513e7f15eab170aac1e1400d878112.jpg@160w_220h_1e_1c", "name": "泰坦尼克号", "actor": "莱昂纳多·迪卡普里奥,凯特·温丝莱特,比利·赞恩", "time": "1998-04-03", "score": "9.5"}
{"index": "6", "image": "https://p0.meituan.net/movie/da64660f82b98cdc1b8a3804e69609e041108.jpg@160w_220h_1e_1c", "name": "唐伯虎点秋香", "actor": "周星驰,巩俐,郑佩佩", "time": "1993-07-01(中国香港)", "score": "9.1"}
{"index": "7", "image": "https://p0.meituan.net/movie/46c29a8b8d8424bdda7715e6fd779c66235684.jpg@160w_220h_1e_1c", "name": "魂断蓝桥", "actor": "费雯·丽,罗伯特·泰勒,露塞尔·沃特森", "time": "1940-05-17(美国)", "score": "9.2"}
{"index": "8", "image": "https://p0.meituan.net/movie/223c3e186db3ab4ea3bb14508c709400427933.jpg@160w_220h_1e_1c", "name": "乱世佳人", "actor": "费雯·丽,克拉克·盖博,奥利维娅·德哈维兰", "time": "1939-12-15(美国)", "score": "9.1"}
{"index": "9", "image": "https://p1.meituan.net/movie/ba1ed511668402605ed369350ab779d6319397.jpg@160w_220h_1e_1c", "name": "天空之城", "actor": "寺田农,鹫尾真知子,龟山助清", "time": "1992", "score": "9.1"}
{"index": "10", "image": "https://p0.meituan.net/movie/b0d986a8bf89278afbb19f6abaef70f31206570.jpg@160w_220h_1e_1c", "name": "辛德勒的名单", "actor": "连姆·尼森,拉尔夫·费因斯,本·金斯利", "time": "1993-12-15(美国)", "score": "9.2"}
{"index": "11", "image": "https://p1.meituan.net/movie/18e3191039d5e71562477659301f04aa61905.jpg@160w_220h_1e_1c", "name": "喜剧之王", "actor": "周星驰,莫文蔚,张柏芝", "time": "1999-02-13(中国香港)", "score": "9.1"}
{"index": "12", "image": "https://p1.meituan.net/movie/14a7b337e8063e3ce05a5993ed80176b74208.jpg@160w_220h_1e_1c", "name": "大闹天宫", "actor": "邱岳峰,毕克,富润生", "time": "1965-12-31", "score": "9.0"}
{"index": "13", "image": "https://p1.meituan.net/movie/6bc004d57358ee6875faa5e9a1239140128550.jpg@160w_220h_1e_1c", "name": "音乐之声", "actor": "朱莉·安德鲁斯,克里斯托弗·普卢默,埃琳诺·帕克", "time": "1965-03-02(美国)", "score": "9.0"}
{"index": "14", "image": "https://p0.meituan.net/movie/ae7245920d95c03765fe1615f3a1fe3865785.jpg@160w_220h_1e_1c", "name": "春光乍泄", "actor": "张国荣,梁朝伟,张震", "time": "1997-05-30(中国香港)", "score": "9.2"}
{"index": "15", "image": "https://p1.meituan.net/movie/6a964e9cee699267053bd6a4bf6f2671195394.jpg@160w_220h_1e_1c", "name": "剪刀手爱德华", "actor": "约翰尼·德普,薇诺娜·瑞德,黛安·韦斯特", "time": "1990-12-06(美国)", "score": "8.8"}
{"index": "16", "image": "https://p0.meituan.net/movie/43d259ecbcd53e8bbe902632772281d6327525.jpg@160w_220h_1e_1c", "name": "美丽人生", "actor": "罗伯托·贝尼尼,尼可莱塔·布拉斯基,乔治·坎塔里尼", "time": "1997-12-20(意大利)", "score": "9.3"}
{"index": "17", "image": "https://p0.meituan.net/movie/2bbaa395c825920fac397706369746e4300686.jpg@160w_220h_1e_1c", "name": "海上钢琴师", "actor": "蒂姆·罗斯,普路特·泰勒·文斯,比尔·努恩", "time": "1998-10-28(意大利)", "score": "9.2"}
{"index": "18", "image": "https://p1.meituan.net/movie/ad974d3527879f00be2eec29135118163728582.jpg@160w_220h_1e_1c", "name": "黑客帝国", "actor": "基努·里维斯,凯瑞-安·莫斯,劳伦斯·菲什伯恩", "time": "2000-01-14", "score": "9.0"}
{"index": "19", "image": "https://p0.meituan.net/movie/932bdfbef5be3543e6b136246aeb99b8123736.jpg@160w_220h_1e_1c", "name": "指环王3:王者无敌", "actor": "伊莱贾·伍德,伊恩·麦克莱恩,丽芙·泰勒", "time": "2004-03-15", "score": "9.2"}
{"index": "20", "image": "https://p1.meituan.net/movie/aacb9ed2a6601bfe515ef0970add1715623792.jpg@160w_220h_1e_1c", "name": "哈利·波特与魔法石", "actor": "丹尼尔·雷德克里夫,鲁伯特·格林特,艾玛·沃特森", "time": "2002-01-26", "score": "9.1"}
{"index": "21", "image": "https://p0.meituan.net/movie/09658109acfea0e248a63932337d8e6a4268980.jpg@160w_220h_1e_1c", "name": "蝙蝠侠:黑暗骑士", "actor": "克里斯蒂安·贝尔,希斯·莱杰,阿伦·伊克哈特", "time": "2008-07-18(美国)", "score": "9.3"}
{"index": "22", "image": "https://p0.meituan.net/movie/8959888ee0c399b0fe53a714bc8a5a17460048.jpg@160w_220h_1e_1c", "name": "楚门的世界", "actor": "金·凯瑞,劳拉·琳妮,诺亚·艾默里奇", "time": "1998-06-01(美国)", "score": "8.9"}
{"index": "23", "image": "https://p0.meituan.net/movie/b05b94b28eca53f325ae8d807fcd4ce01798036.jpg@160w_220h_1e_1c", "name": "加勒比海盗", "actor": "约翰尼·德普,凯拉·奈特莉,奥兰多·布鲁姆", "time": "2003-11-21", "score": "8.9"}
{"index": "24", "image": "https://p1.meituan.net/movie/53b6f0b66882a53b08896c92076515a8236400.jpg@160w_220h_1e_1c", "name": "射雕英雄传之东成西就", "actor": "张国荣,梁朝伟,张学友", "time": "1993-02-05(中国香港)", "score": "8.9"}
{"index": "25", "image": "https://p0.meituan.net/movie/606de8f394d40dbcbb9b87943fec71a2130408.jpg@160w_220h_1e_1c", "name": "无间道", "actor": "刘德华,梁朝伟,黄秋生", "time": "2003-09-05", "score": "9.1"}
{"index": "26", "image": "https://p0.meituan.net/movie/bb1dee5e0b25889a2410211c1d5010ae190824.jpg@160w_220h_1e_1c", "name": "教父2", "actor": "阿尔·帕西诺,罗伯特·德尼罗,黛安·基顿", "time": "1974-12-12(美国)", "score": "9.0"}
{"index": "27", "image": "https://p0.meituan.net/movie/267dd2483f0fb57081474c00fbea38451415571.jpg@160w_220h_1e_1c", "name": "机器人总动员", "actor": "本·贝尔特,艾丽莎·奈特,杰夫·格尔林", "time": "2008-06-27(美国)", "score": "9.3"}
{"index": "28", "image": "https://p1.meituan.net/movie/dd08154878aac7c8c649fe3eeb8ccd0a2498277.jpg@160w_220h_1e_1c", "name": "指环王1:护戒使者", "actor": "伊莱贾·伍德,伊恩·麦克莱恩,丽芙·泰勒", "time": "2002-04-04", "score": "9.0"}
{"index": "29", "image": "https://p0.meituan.net/movie/02bb9fd161c05bad6089133098efcdb5546589.jpg@160w_220h_1e_1c", "name": "指环王2:双塔奇兵", "actor": "伊莱贾·伍德,伊恩·麦克莱恩,丽芙·泰勒", "time": "2003-04-25", "score": "9.1"}
{"index": "30", "image": "https://p0.meituan.net/movie/27b76fe6cf3903f3d74963f70786001e1438406.jpg@160w_220h_1e_1c", "name": "狮子王", "actor": "马修·布罗德里克,尼基塔·卡兰姆,詹姆斯·厄尔·琼斯", "time": "1995-07-15", "score": "8.8"}
{"index": "31", "image": "https://p0.meituan.net/movie/76fc92cfa6c8f2959431b8aa604ef7ae126414.jpg@160w_220h_1e_1c", "name": "天堂电影院", "actor": "菲利浦·诺瓦雷,赛尔乔·卡斯特利托,蒂兹亚娜·罗达托", "time": "1988-11-17(意大利)", "score": "9.2"}
{"index": "32", "image": "https://p0.meituan.net/movie/4c41068ef7608c1d4fbfbe6016e589f7204391.jpg@160w_220h_1e_1c", "name": "活着", "actor": "葛优,巩俐,牛犇", "time": "1994-05-18(法国)", "score": "9.0"}
{"index": "33", "image": "https://p1.meituan.net/movie/a2a287c77415dc1f85b04d288f7d63ab1089754.jpg@160w_220h_1e_1c", "name": "拯救大兵瑞恩", "actor": "汤姆·汉克斯,马特·达蒙,汤姆·塞兹摩尔", "time": "1998-11-13", "score": "8.9"}
{"index": "34", "image": "https://p0.meituan.net/movie/0127b451d5b8f0679c6f81c8ed414bb2432442.jpg@160w_220h_1e_1c", "name": "哈尔的移动城堡", "actor": "倍赏千惠子,木村拓哉,美轮明宏", "time": "2004-11-20(日本)", "score": "9.0"}
{"index": "35", "image": "https://p0.meituan.net/movie/7787c10ad5e95b03cf83ef9473500d8e282796.jpg@160w_220h_1e_1c", "name": "忠犬八公的故事", "actor": "Forest,理查·基尔,琼·艾伦", "time": "2010-03-12(英国)", "score": "9.3"}
{"index": "36", "image": "https://p1.meituan.net/movie/bc022b86345c643ca21d759166f77a553679589.jpg@160w_220h_1e_1c", "name": "疯狂原始人", "actor": "尼古拉斯·凯奇,艾玛·斯通,瑞安·雷诺兹", "time": "2013-04-20", "score": "9.5"}
{"index": "37", "image": "https://p1.meituan.net/movie/2f344a9f9575edbcae9f0abe0578bc90339773.jpg@160w_220h_1e_1c", "name": "盗梦空间", "actor": "莱昂纳多·迪卡普里奥,渡边谦,约瑟夫·高登-莱维特", "time": "2010-09-01", "score": "9.2"}
{"index": "38", "image": "https://p0.meituan.net/movie/a08f65e6cb50fab32df5da69ff116f593095363.jpg@160w_220h_1e_1c", "name": "幽灵公主", "actor": "松田洋治,石田百合子,田中裕子", "time": "1998-05-01", "score": "8.9"}
{"index": "39", "image": "https://p1.meituan.net/movie/7e471a9171a410ebc9413b2f1de67afc130067.jpg@160w_220h_1e_1c", "name": "东邪西毒", "actor": "张国荣,梁朝伟,刘嘉玲", "time": "1994-09-17", "score": "8.8"}
{"index": "40", "image": "https://p1.meituan.net/movie/91f575ec93f019f428d1f33e3ceca7c5115495.jpg@160w_220h_1e_1c", "name": "阿凡达", "actor": "萨姆·沃辛顿,佐伊·索尔达娜,米歇尔·罗德里格兹", "time": "2010-01-04", "score": "9.0"}
{"index": "41", "image": "https://p0.meituan.net/movie/b3defc07dfaa1b6f5b74852ce38a3f8f242792.jpg@160w_220h_1e_1c", "name": "搏击俱乐部", "actor": "爱德华·哈里森·诺顿,布拉德·皮特,海伦娜·伯翰·卡特", "time": "1999-10-15(美国)", "score": "8.8"}
{"index": "42", "image": "https://p0.meituan.net/movie/4f9638ba234c3fb673f23a09968db875371576.jpg@160w_220h_1e_1c", "name": "风之谷", "actor": "岛本须美,永井一郎,坂本千夏", "time": "1992", "score": "8.9"}
{"index": "43", "image": "https://p1.meituan.net/movie/06ec3c1c647942b1e40bca84036014e9490863.jpg@160w_220h_1e_1c", "name": "V字仇杀队", "actor": "娜塔莉·波特曼,雨果·维文,斯蒂芬·瑞", "time": "2006-03-17(美国)", "score": "8.8"}
{"index": "44", "image": "https://p0.meituan.net/movie/df15efd261060d3094a73ef679888d4f238149.jpg@160w_220h_1e_1c", "name": "十二怒汉", "actor": "亨利·方达,李·科布,马丁·鲍尔萨姆", "time": "1957-04-13(美国)", "score": "9.1"}
{"index": "45", "image": "https://p1.meituan.net/movie/5896de3c1474277730e321c9b1db04a9205644.jpg@160w_220h_1e_1c", "name": "当幸福来敲门", "actor": "威尔·史密斯,贾登·史密斯,坦迪·牛顿", "time": "2008-01-17", "score": "8.9"}
{"index": "46", "image": "https://p0.meituan.net/movie/b0d97e4158b47d653d7a81d66f7dd3092146907.jpg@160w_220h_1e_1c", "name": "驯龙高手", "actor": "杰伊·巴鲁切尔,杰拉德·巴特勒,亚美莉卡·费雷拉", "time": "2010-05-14", "score": "9.0"}
{"index": "47", "image": "https://p0.meituan.net/movie/845ce32778a1b3f258de089f91a3979b5766154.jpg@160w_220h_1e_1c", "name": "速度与激情5", "actor": "范·迪塞尔,保罗·沃克,道恩·强森", "time": "2011-05-12", "score": "9.2"}
{"index": "48", "image": "https://p0.meituan.net/movie/70de97ebb6b5251ecb7c3f6d7a782a7f189340.jpg@160w_220h_1e_1c", "name": "放牛班的春天", "actor": "热拉尔·朱尼奥,让-巴蒂斯特·莫尼耶,玛丽·布奈尔", "time": "2004-10-16", "score": "8.8"}
{"index": "49", "image": "https://p1.meituan.net/movie/f8e9d5a90224746d15dfdbd53d4fae3d209420.jpg@160w_220h_1e_1c", "name": "勇敢的心", "actor": "梅尔·吉布森,苏菲·玛索,帕特里克·麦高汉", "time": "1995-05-24(美国)", "score": "8.8"}
{"index": "50", "image": "https://p0.meituan.net/movie/85c2bfba6025bfbfb53291ae5924c215308805.jpg@160w_220h_1e_1c", "name": "神偷奶爸", "actor": "史蒂夫·卡瑞尔,杰森·席格尔,拉塞尔·布兰德", "time": "2010-07-09(美国)", "score": "9.0"}
{"index": "51", "image": "https://p1.meituan.net/movie/8d7b0b902afd4ec1a3dd7a9c6149463c187734.jpg@160w_220h_1e_1c", "name": "闻香识女人", "actor": "阿尔·帕西诺,克里斯·奥唐纳,加布里埃尔·安瓦尔", "time": "1992-12-23(美国)", "score": "8.8"}
{"index": "52", "image": "https://p1.meituan.net/movie/ca4a128a5a54d5b5e35ceba622636c831810197.jpg@160w_220h_1e_1c", "name": "三傻大闹宝莱坞", "actor": "阿米尔·汗,黄渤,卡琳娜·卡普", "time": "2011-12-08", "score": "9.1"}
{"index": "53", "image": "https://p0.meituan.net/movie/e71affe126eeb4f8bfcc738cbddeebc8288766.jpg@160w_220h_1e_1c", "name": "断背山", "actor": "希斯·莱杰,杰克·吉伦哈尔,米歇尔·威廉姆斯", "time": "2006-01-13(美国)", "score": "9.0"}
{"index": "54", "image": "https://p0.meituan.net/movie/2e383b5f5f306f10f9f26d9f1c28cf1d825537.jpg@160w_220h_1e_1c", "name": "黑客帝国3:矩阵革命", "actor": "基努·里维斯,雨果·维文,凯瑞-安·莫斯", "time": "2003-11-05", "score": "8.8"}
{"index": "55", "image": "https://p0.meituan.net/movie/34998e31c6d07475f1add6b8b16fd21d192579.jpg@160w_220h_1e_1c", "name": "少年派的奇幻漂流", "actor": "苏拉·沙玛,伊尔凡·可汗,塔布", "time": "2012-11-22", "score": "9.1"}
{"index": "56", "image": "https://p0.meituan.net/movie/47dd790e19dad72b50580641de5608c5199014.jpg@160w_220h_1e_1c", "name": "飞屋环游记", "actor": "爱德华·阿斯纳,乔丹·长井,鲍勃·彼德森", "time": "2009-08-04", "score": "8.9"}
{"index": "57", "image": "https://p1.meituan.net/movie/21b9211eb1094af360842472018db634286646.jpg@160w_220h_1e_1c", "name": "末代皇帝", "actor": "尊龙,陈冲,彼得·奥图尔", "time": "1987-10-23", "score": "8.8"}
{"index": "58", "image": "https://p1.meituan.net/movie/0b507aa44c4dfbbcc91949b69b1b39a168922.jpg@160w_220h_1e_1c", "name": "鬼子来了", "actor": "姜文,姜宏波,陈强", "time": "2000-05-12(法国戛纳)", "score": "8.9"}
{"index": "59", "image": "https://p0.meituan.net/movie/92eb862c42c49f8e41e459c369c4512b226610.jpg@160w_220h_1e_1c", "name": "大话西游之月光宝盒", "actor": "周星驰,莫文蔚,吴孟达", "time": "2014-10-24", "score": "9.6"}
{"index": "60", "image": "https://p0.meituan.net/movie/15f1ac49b6d1ff7b71207672993ed6901536456.jpg@160w_220h_1e_1c", "name": "怦然心动", "actor": "玛德琳·卡罗尔,卡兰·麦克奥利菲,艾丹·奎因", "time": "2010-08-06(美国)", "score": "8.9"}
{"index": "61", "image": "https://p1.meituan.net/movie/75c0d3eb584be030a01f2e26741a8f41251454.jpg@160w_220h_1e_1c", "name": "致命魔术", "actor": "休·杰克曼,克里斯蒂安·贝尔,迈克尔·凯恩", "time": "2006-10-20(美国)", "score": "8.8"}
{"index": "62", "image": "https://p0.meituan.net/movie/7b7d1f8aa36d7a15463ce6942708a1a7265296.jpg@160w_220h_1e_1c", "name": "美丽心灵", "actor": "罗素·克洛,詹妮弗·康纳利,艾德·哈里斯", "time": "2001-12-21(美国)", "score": "8.8"}
{"index": "63", "image": "https://p0.meituan.net/movie/fcc17667b8343131101eeb4c67d90bf9150883.jpg@160w_220h_1e_1c", "name": "无敌破坏王", "actor": "约翰·C·赖利,萨拉·西尔弗曼,简·林奇", "time": "2012-11-06", "score": "9.1"}
{"index": "64", "image": "https://p1.meituan.net/movie/96d98200d2afb4b87ff189f9c15b6545568339.jpg@160w_220h_1e_1c", "name": "倩女幽魂", "actor": "张国荣,王祖贤,午马", "time": "2011-04-30", "score": "9.2"}
{"index": "65", "image": "https://p0.meituan.net/movie/7ec873ba943f13e3c63789d899bd0e23256871.jpg@160w_220h_1e_1c", "name": "夜访吸血鬼", "actor": "汤姆·克鲁斯,布拉德·皮特,克尔斯滕·邓斯特", "time": "1994-11-11(美国)", "score": "8.8"}
{"index": "66", "image": "https://p1.meituan.net/movie/96bb58f3e9d213fb0438987d16d27561379209.jpg@160w_220h_1e_1c", "name": "蝙蝠侠:黑暗骑士崛起", "actor": "克里斯蒂安·贝尔,迈克尔·凯恩,加里·奥德曼", "time": "2012-08-27", "score": "8.9"}
{"index": "67", "image": "https://p1.meituan.net/movie/484171372de45945e8bbbcc97db57e09136701.jpg@160w_220h_1e_1c", "name": "钢琴家", "actor": "艾德里安·布洛迪,艾米莉娅·福克斯,米哈乌·热布罗夫斯基", "time": "2002-09-25(法国)", "score": "8.8"}
{"index": "68", "image": "https://p0.meituan.net/movie/2526f77c650bf7cf3d5ee2dccdeac332244951.jpg@160w_220h_1e_1c", "name": "本杰明·巴顿奇事", "actor": "布拉德·皮特,凯特·布兰切特,塔拉吉·P·汉森", "time": "2008-12-25(美国)", "score": "8.8"}
{"index": "69", "image": "https://p1.meituan.net/movie/bb0eca029cd25329776a4549b3fbe262924727.jpg@160w_220h_1e_1c", "name": "哈利·波特与死亡圣器(下)", "actor": "丹尼尔·雷德克里夫,鲁伯特·格林特,艾玛·沃特森", "time": "2011-08-04", "score": "9.0"}
{"index": "70", "image": "https://p1.meituan.net/movie/0b0d45b58946078dd24d4945dd6be3b51329411.jpg@160w_220h_1e_1c", "name": "甜蜜蜜", "actor": "黎明,张曼玉,曾志伟", "time": "2015-02-13", "score": "9.2"}
{"index": "71", "image": "https://p1.meituan.net/movie/7ed07b8ea8c0e0d0c7b685d20e3ec64e232004.jpg@160w_220h_1e_1c", "name": "初恋这件小事", "actor": "马里奥·毛瑞尔,平采娜·乐维瑟派布恩,阿查拉那·阿瑞亚卫考", "time": "2012-06-05", "score": "8.8"}
{"index": "72", "image": "https://p1.meituan.net/movie/1e700e53e4fe29dd5942381bb353c8532239179.jpg@160w_220h_1e_1c", "name": "触不可及", "actor": "弗朗索瓦·克鲁塞,奥玛·希,安娜·勒尼", "time": "2011-11-02(法国)", "score": "9.1"}
{"index": "73", "image": "https://p1.meituan.net/movie/7833126c8c21a11571bb52fbdece0acb811449.jpg@160w_220h_1e_1c", "name": "新龙门客栈", "actor": "张曼玉,梁家辉,甄子丹", "time": "2012-02-24", "score": "8.8"}
{"index": "74", "image": "https://p1.meituan.net/movie/2a0783b4fd95566568f24adfad2181bb5392280.jpg@160w_220h_1e_1c", "name": "熔炉", "actor": "孔刘,郑有美,金智英", "time": "2011-09-22(韩国)", "score": "8.8"}
{"index": "75", "image": "https://p1.meituan.net/movie/dc2246233a6f5ac1e34c7176b602c8ca174557.jpg@160w_220h_1e_1c", "name": "大话西游之大圣娶亲", "actor": "周星驰,朱茵,莫文蔚", "time": "2014-10-24", "score": "8.8"}
{"index": "76", "image": "https://p1.meituan.net/movie/135c612860fae899df2220149664d97a173555.jpg@160w_220h_1e_1c", "name": "小鞋子", "actor": "默罕默德·阿米尔·纳吉,Kamal Mirkarimi,Behzad Rafi", "time": "1999-01-22(美国)", "score": "9.0"}
{"index": "77", "image": "https://p0.meituan.net/movie/1199dc6273680f175fd9b06c9c36d08a219658.jpg@160w_220h_1e_1c", "name": "教父", "actor": "马龙·白兰度,阿尔·帕西诺,詹姆斯·肯恩", "time": "2015-04-18", "score": "9.3"}
{"index": "78", "image": "https://p0.meituan.net/movie/19653e8af59cf473cd40f9ccc0658d93692304.jpg@160w_220h_1e_1c", "name": "素媛", "actor": "李来,薛耿求,严志媛", "time": "2013-10-02(韩国)", "score": "9.1"}
{"index": "79", "image": "https://p0.meituan.net/movie/5420be40e3b755ffe04779b9b199e935256906.jpg@160w_220h_1e_1c", "name": "萤火之森", "actor": "内山昂辉,佐仓绫音,后藤弘树", "time": "2011-09-17(日本)", "score": "9.0"}
{"index": "80", "image": "https://p1.meituan.net/movie/d5970e36c8868a4b746c80f3b3f8a404174615.jpg@160w_220h_1e_1c", "name": "穿条纹睡衣的男孩", "actor": "阿沙·巴特菲尔德,维拉·法梅加,大卫·休里斯", "time": "2008-09-12(英国)", "score": "9.0"}
{"index": "81", "image": "https://p0.meituan.net/movie/3985eaf3858bea0f2a3d966bf7ee2103178217.jpg@160w_220h_1e_1c", "name": "窃听风暴", "actor": "乌尔里希·穆埃,塞巴斯蒂安·科赫,马蒂娜·格德克", "time": "2006-03-23(德国)", "score": "9.0"}
{"index": "82", "image": "https://p0.meituan.net/movie/4abc8c932cfacfc0089e2883765d02d1295222.jpg@160w_220h_1e_1c", "name": "时空恋旅人", "actor": "瑞秋·麦克亚当斯,多姆纳尔·格里森,比尔·奈伊", "time": "2013-09-04(英国)", "score": "8.9"}
{"index": "83", "image": "https://p1.meituan.net/movie/6a6e74b2c289f9fa4433dd2dc04a7741331638.jpg@160w_220h_1e_1c", "name": "7号房的礼物", "actor": "柳承龙,郑镇荣,朴信惠", "time": "2013-01-23(韩国)", "score": "8.9"}
{"index": "84", "image": "https://p0.meituan.net/movie/b5ff0216e689b3fcc065590c48cd5105255305.jpg@160w_220h_1e_1c", "name": "恐怖直播", "actor": "河正宇,李璟荣,李大为", "time": "2013-07-31(韩国)", "score": "8.8"}
{"index": "85", "image": "https://p0.meituan.net/movie/7373dbba07b50ce6f24336edb96b2ea4271536.jpg@160w_220h_1e_1c", "name": "海豚湾", "actor": "里克·奥巴瑞,路易·西霍尤斯,哈迪·琼斯", "time": "2009-07-31(美国)", "score": "8.9"}
{"index": "86", "image": "https://p1.meituan.net/movie/c835b3588d0061ed3b992388a0a96f15160913.jpg@160w_220h_1e_1c", "name": "忠犬八公物语", "actor": "仲代达矢,春川真澄,井川比佐志", "time": "1987-08-01(日本)", "score": "9.0"}
{"index": "87", "image": "https://p1.meituan.net/movie/b553d13f30100db731ab6cf45668e52d94703.jpg@160w_220h_1e_1c", "name": "上帝之城", "actor": "亚历桑德雷·罗德里格斯,艾莉丝·布拉加,莱安德鲁·菲尔米诺", "time": "2002-08-30(巴西)", "score": "8.9"}
{"index": "88", "image": "https://p1.meituan.net/movie/92198a6fc8c3f5d13aa1bdf203572c0f99438.jpg@160w_220h_1e_1c", "name": "美国往事", "actor": "罗伯特·德尼罗,詹姆斯·伍兹,伊丽莎白·麦戈文", "time": "2015-04-23", "score": "9.1"}
{"index": "89", "image": "https://p1.meituan.net/movie/4ffca83fd972f71e291f8ea8d78a4b58594878.jpg@160w_220h_1e_1c", "name": "七武士", "actor": "三船敏郎,志村乔,千秋实", "time": "1954-04-26(日本)", "score": "9.1"}
{"index": "90", "image": "https://p1.meituan.net/movie/30310858fdab34c7a17cfd7ec8ad8bfc112201.jpg@160w_220h_1e_1c", "name": "完美的世界", "actor": "凯文·科斯特纳,克林特·伊斯特伍德,T·J·劳瑟", "time": "1993-11-24(美国)", "score": "8.9"}
{"index": "91", "image": "https://p1.meituan.net/movie/2c0a5fedf4b43d142121b91c6ccabe1b59051.jpg@160w_220h_1e_1c", "name": "一一", "actor": "吴念真,金燕玲,李凯莉", "time": "2000-09-20(法国)", "score": "8.9"}
{"index": "92", "image": "https://p0.meituan.net/movie/3e5f5f3aa4b7e5576521e26c2c7c894d253975.jpg@160w_220h_1e_1c", "name": "英雄本色", "actor": "狄龙,张国荣,周润发", "time": "2017-11-17", "score": "9.2"}
{"index": "93", "image": "https://p0.meituan.net/movie/885fc379c614a2b4175587b95ac98eb95045650.jpg@160w_220h_1e_1c", "name": "阿飞正传", "actor": "张国荣,张曼玉,刘德华", "time": "2018-06-25", "score": "8.8"}
{"index": "94", "image": "https://p1.meituan.net/movie/36a893c53a13f9bb934071b86ae3b5c492427.jpg@160w_220h_1e_1c", "name": "爱·回家", "actor": "俞承豪,金艺芬,童孝熙", "time": "2002-04-05(韩国)", "score": "9.0"}
{"index": "95", "image": "https://p0.meituan.net/movie/0018b57299d0d4540330a31244c880a9112971.jpg@160w_220h_1e_1c", "name": "海洋", "actor": "雅克·贝汉,姜文,兰斯洛特·佩林", "time": "2011-08-12", "score": "9.0"}
{"index": "96", "image": "https://p1.meituan.net/movie/ed50b58bf636d207c56989872a91f4cf305138.jpg@160w_220h_1e_1c", "name": "我爱你", "actor": "宋在浩,李顺才,尹秀晶", "time": "2011-02-17(韩国)", "score": "9.0"}
{"index": "97", "image": "https://p0.meituan.net/movie/cd18ed2c5cda9e71e17e5e6ef61ced172912303.jpg@160w_220h_1e_1c", "name": "黄金三镖客", "actor": "克林特·伊斯特伍德,李·范·克里夫,埃里·瓦拉赫", "time": "1966-12-23(意大利)", "score": "8.9"}
{"index": "98", "image": "https://p1.meituan.net/movie/a1634f4e49c8517ae0a3e4adcac6b0dc43994.jpg@160w_220h_1e_1c", "name": "迁徙的鸟", "actor": "雅克·贝汉,Philippe Labro", "time": "2001-12-12(法国)", "score": "9.1"}
{"index": "99", "image": "https://p0.meituan.net/movie/c304c687e287c7c2f9e22cf78257872d277201.jpg@160w_220h_1e_1c", "name": "龙猫", "actor": "秦岚,糸井重里,岛本须美", "time": "2018-12-14", "score": "9.1"}
{"index": "100", "image": "https://p0.meituan.net/movie/30b20139e68c46d02e0893277d633b701292458.jpg@160w_220h_1e_1c", "name": "千与千寻", "actor": "柊瑠美,周冬雨,入野自由", "time": "2019-06-21", "score": "9.3"}

 





完整代码

import requests
import re
import json
from requests.exceptions import RequestException
from multiprocessing import  Pool



class maoyan():

    # 获取单个网页html
    def get_one_page(self,url):
        try:
            response =requests.get(url)
            if response.status_code==200:
                return response.text
            return None
        except RequestException:
            return None
    # 利用正则表达式解析
    def pare_one_page(self,html):
        pattern = re.compile(
'<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)"'
   '.*?name"><a.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)'
     '</p>.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>',re.S)

items = re.findall(pattern,html) for item in items: yield { # 索引 'index':item[0], # 封面 'image':item[1], # 电影名称 'name': item[2], # 演员 'actor': item[3].strip()[3:], # 上映时间 'time': item[4].strip()[5:], # 评分 'score': item[5]+item[6] } # 写入文件 def write_to_file(self,content): with open('maoyan.txt','a',encoding='utf-8') as f: f.write(json.dumps(content,ensure_ascii=False)+'\n') f.close() def main(self,offset): # 猫眼电影TOP榜url拼接 url = 'https://maoyan.com/board/4?offset='+str(offset) html = self.get_one_page(url) for item in self.pare_one_page(html): self.write_to_file(item) print(item) if __name__ == '__main__': m = maoyan() for i in range(10): m.main(i*10) # pool = Pool() # pool.map(m.main,[i*10 for i in range(10)])

 








posted on 2019-07-22 20:24  bdcyouth  阅读(401)  评论(0编辑  收藏

导航

统计