import re
import requests
import ua_info
import random
from lxml import etree
import json
from pprint import pprint"""
author:"lihongyuan"
function:爬取豆瓣电影排行榜
"""class DoubanSpider():def __init__(self):self.url='https://movie.douban.com/chart'#获取电影类型和类型码def getFilmTypeDict(self):html = requests.get(url=self.url, headers={'User-Agent': random.choice(ua_info.ua_list)}).text   #返回解码后的页面#tree=etree.HTML(html) #解析为DOM#xpath寻找电影类型 #搜索针对的是页面对象解码后再解析为树节点# type_li= tree.xpath('//div[@class="types"]/span/a/@href')# print(type_li)#正则寻找电影类型#搜索匹配正则表达式要求的字符串 #搜索范围为当前页面解码后str_li=re.findall(r'/typerank\?type_name=(.*?)&type=(\d*?)&interval_id=100:90&action=',html)#print(str_li)#将类型和类型码存入字典type_dict={}for tuple in str_li:type_dict[tuple[0]]=tuple[1]return type_dict#获取电影总数def filmTotalNumber(self,type_code):url ='https://movie.douban.com/j/chart/top_list_count?type='+type_code+'&interval_id=100%3A90'html = requests.get(url=url, headers={'User-Agent': random.choice(ua_info.ua_list)}).text #不是字典,是字符串!{"playable_count":310,"total":376,"unwatched_count":376}'dict=json.loads(html)   #将json的字符串转化为python的字典 #json是javascript object notation的意思,用于服务器和客户端之间传输数据return dict['total']#主函数#获取电影信息def run(self,type):file = open(r'D:\PycharmProjects\爬虫Project\typefilminfo.json', 'a+', encoding='UTF-8',newline='')type_dict =self.getFilmTypeDict()json.dump(type_dict,file,ensure_ascii=False)    #ensure_ascii需要设置为false,禁用ASCII,可以显示中文  #将python对象转化成json字符串写入文件file.write('\r\n')type_code = type_dict[type]total=self.filmTotalNumber(type_code)for i in range(0,total,20):url = 'https://movie.douban.com/j/chart/top_list?type='+type_code+'&interval_id=100%3A90'+'&action=&start='+str(i)+'&limit=20'html=requests.get(url=url, headers={'User-Agent': random.choice(ua_info.ua_list)}).text #返回的json格式的字符串[{"rating":["9.4","50"],"rank":1,"cover_url":"https://img2.doubanio.com\/view\/photo\/s_ratio_poster\/public\/p511118051.jpg","is_playable":true,"id":"1295644","types":["剧情","动作","犯罪"],"regions":["法国","美国"],"title":"这个杀手不太冷","url":"https:\/\/movie.douban.com\/subject\/1295644\/","release_date":"1994-09-14","actor_count":22,"vote_count":2242296,"score":"9.4","actors":["让·雷诺","娜塔莉·波特曼","加里·奥德曼","丹尼·爱罗","彼得·阿佩尔","迈克尔·巴达鲁科","艾伦·格里尼","伊丽莎白·瑞根","卡尔·马图斯维奇","弗兰克·赛格","麦温","乔治·马丁","罗伯特·拉萨多","亚当·布斯奇","马里奥·托迪斯科","萨米·纳塞利","让·雨果·安格拉德","埃莱娜·卡多纳","沈晓谦","大塚明夫","Keith A. Glascoe","Arsène Jiroyan"],"is_watched":false},{"rating":["9.3","50"],"rank":2,"cover_url":"https://img2.doubanio.com\/view\/photo\/s_ratio_poster\/public\/p2642829472.jpg","is_playable":true,"id":"1291552","types":["剧情","动作","奇幻","冒险"],"regions":["美国","新西兰"],"title":"指环王3:王者无敌","url":"https:\/\/movie.douban.com\/subject\/1291552\/","release_date":"2004-03-12","actor_count":67,"vote_count":782479,"score":"9.3","actors":["伊利亚·伍德","西恩·奥斯汀","维果·莫腾森","奥兰多·布鲁姆","伊恩·麦克莱恩","肖恩·宾","多米尼克·莫纳汉","丽芙·泰勒","约翰·贝西","凯特·布兰切特","比利·博伊德","萨德文·布罗菲","阿利斯泰尔·布朗宁","马尔顿·索克斯","伯纳德·希尔","伊安·霍姆","布鲁斯·霍普金斯","Ian Hughes","劳伦斯·马克奥雷","诺埃尔·阿普利比","布雷特·麦肯齐","Alexandra Astin","Sarah McLeod","Maisy McLeod-Riera","约翰·诺贝尔","Paul Norell","米兰达·奥图","布鲁斯·菲利普斯","沙恩·朗吉","约翰·瑞斯-戴维斯","Todd Rippon","安迪·瑟金斯","Harry Sinclair","乔尔·托贝克","卡尔·厄本","史蒂芬·乌瑞","雨果·维文","大卫·文翰","阿兰·霍华德","萨拉·贝克","Robert Pollock","佩特·史密斯","杰德·布罗菲","菲利普·格里夫","布拉德·道里夫","克里斯托弗·李","布鲁斯·斯宾斯","吉诺·阿赛维多","Jarl Benzon","Jørn Benzon","Robert Catto","Michael Elsworth","彼得·杰克逊","Sandro Kopp","安德鲁·莱斯尼","约瑟夫·米卡-亨特","亨利·莫腾森","克雷格·帕克","克里斯蒂安·瑞沃斯","迈克尔·斯曼内科 ","霍华德·肖","约翰·斯蒂芬森","理查德·泰勒","周志强","张磊","姜广涛","金永钢"],"is_watched":false},{"rating":["9.2","50"],"rank":3,"cover_url":"https://img2.doubanio.com\/view\/photo\/s_ratio_poster\/public\/p462657443.jpg","is_playable":true,"id":"1851857","types":["剧情","动作","科幻","犯罪","惊悚"],"regions":["美国","英国"],"title":"蝙蝠侠:黑暗骑士","url":"https:\/\/movie.douban.com\/subject\/1851857\/","release_date":"2008-07-14","actor_count":40,"vote_count":1030205,"score":"9.2","actors":["克里斯蒂安·贝尔","希斯·莱杰","艾伦·艾克哈特","迈克尔·凯恩","玛吉·吉伦哈尔","加里·奥德曼","摩根·弗里曼","莫尼克·加布里埃拉·库尔内","罗恩·迪恩","基里安·墨菲","黄经汉","内斯特·卡博内尔","埃里克·罗伯茨","里特奇·科斯特","安东尼·迈克尔·豪尔","基斯·斯扎拉巴基克","柯林·麦克法兰","约书亚·哈尔托","美琳达·麦格劳","内森·甘宝","迈克尔·维约","迈克尔·斯托扬诺夫","威廉·斯米利","丹尼·高德林","迈克尔·加·怀特","马修·奥尼尔","威廉·菲克纳","欧鲁米基·欧拉乌米","格雷格·比姆","爱利克·赫尔曼","毕崔斯·罗森","文森佐·尼克力","陈冠希","玛丽扎·卡布蕾拉","Tina Simmons","罗南·萨莫尔斯","利萨·麦克阿里斯特","大卫·达斯马齐连","理查德·迪兰","亚当·卡莱佩里斯"],"is_watched":false},{"rating":["9.2","45"],"rank":4,"cover_url":"https://img9.doubanio.com\/view\/photo\/s_ratio_poster\/public\/p2640236255.jpg","is_playable":true,"id":"1291572","types":["剧情","动作","奇幻","冒险"],"regions":["美国","新西兰"],"title":"指环王2:双塔奇兵","url":"https:\/\/movie.douban.com\/subject\/1291572\/","release_date":"2003-04-25","actor_count":58,"vote_count":732839,"score":"9.2","actors":["伊利亚·伍德","西恩·奥斯汀","多米尼克·莫纳汉","奥兰多·布鲁姆","维果·莫腾森","伊恩·麦克莱恩","凯特·布兰切特","比利·博伊德","杰德·布罗菲","丽芙·泰勒","安迪·瑟金斯","米兰达·奥图","雨果·维文","布拉德·道里夫","卡卢姆·吉廷斯","伯纳德·希尔","布鲁斯·霍普金斯","克里斯托弗·李","纳撒尼尔·利斯","罗宾·马尔科姆","约翰·贝西","萨拉·贝克","克雷格·帕克","布鲁斯·菲利普斯","Robert Pollock","约翰·瑞斯-戴维斯","奥利维亚·田內","卡尔·厄本","史蒂芬·乌瑞","大卫·文翰","菲利普·格里夫","肖恩·宾","约翰·诺贝尔","Jarl Benzon","Jørn Benzon","Ben Britton","阿利斯泰尔·布朗宁","Sean Button","Robert Catto","罗德尼·库克","卡尔洛斯·德林克沃特","西奥沙福瓦","本·弗兰舍姆","Jonathan Harding","Lucas Hayward","丹·汉纳","保罗·霍姆斯","杰森霍德","彼得·杰克逊","Sam Kelly","Sandro Kopp","姜广涛","张磊","陆建艺","金永钢","劳伦斯·马克奥雷","布鲁克·奥佩斯","周志强"],"is_watched":false},{"rating":["9.3","50"],"rank":5,"cover_url":"https://img9.doubanio.com\/view\/photo\/s_ratio_poster\/public\/p2215886505.jpg","is_playable":true,"id":"1295399","types":["动作","冒险","剧情"],"regions":["日本"],"title":"七武士","url":"https:\/\/movie.douban.com\/subject\/1295399\/","release_date":"1954-04-26","actor_count":49,"vote_count":191870,"score":"9.3","actors":["三船敏郎","志村乔","津岛惠子","岛崎雪子","藤原釜足","加东大介","木村功","千秋实","宫口精二","小杉义男","左卜全","稻叶义男","土屋嘉男","高堂国典","东野英治郎","上田吉二郎","多多良纯","渡边笃","小川虎之助","山形勋","上山草人","清水元","高木新平","大友伸","高原骏雄","稻垣三郎","堺左千夫","千石规子","本间文子","大久保正信","伊藤实","大村千吉","广濑正一","宇野晃司","谷晃","中岛春雄","清水美恵","熊谷卓三","夏木顺平","岩本弘司","堤康久","马野都留子","森今日子","加藤武","仲代达矢","宇津井健","山本廉","林幹","东静子"],"is_watched":false},{"rating":["9.1","45"],"rank":6,"cover_url":"https://img9.doubanio.com\/view\/photo\/s_ratio_poster\/public\/p2373910134.jpg","is_playable":true,"id":"1291571","types":["剧情","动作","奇幻","冒险"],"regions":["新西兰","美国"],"title":"指环王1:护戒使者","url":"https:\/\/movie.douban.com\/subject\/1291571\/","release_date":"2002-04-04","actor_count":54,"vote_count":824954,"score":"9.1","actors":["伊利亚·伍德","西恩·奥斯汀","伊恩·麦克莱恩","维果·莫腾森","奥兰多·布鲁姆","多米尼克·莫纳汉","比利·博伊德","克里斯托弗·李","马尔顿·索克斯","梅根·爱德华兹","伊安·霍姆","凯特·布兰切特","阿兰·霍华德","马克·弗格森","肖恩·宾","萨拉·贝克","劳伦斯·马克奥雷","安迪·瑟金斯","彼得·麦肯齐","伊恩·穆内","克雷格·帕克","卡梅隆·罗德","约翰·瑞斯-戴维斯","丽芙·泰勒","大卫·韦瑟莱","雨果·维文","菲利普·格里夫","威廉·约翰逊","伊丽莎白·穆迪","布莱恩·瑟金特","杰德·布罗菲","诺曼·凯茨","兰德尔·威廉·库克","萨比恩·克洛森","西奥沙福瓦","本·弗兰舍姆","彼得·杰克逊","艾伦·李","诺埃尔·阿普利比","Michael Elsworth","Sarah McLeod","马丁·桑德森","Harry Sinclair","吉诺·阿赛维多","Jarl Benzon","Jørn Benzon","Ben Britton","Jonathan Harding","Taea Hartwell","Sam Kelly","姜广涛","张磊","周志强","布雷特·麦肯齐"],"is_watched":false},{"rating":["9.1","45"],"rank":7,"cover_url":"https://img1.doubanio.com\/view\/photo\/s_ratio_poster\/public\/p451926968.jpg","is_playable":false,"id":"1291843","types":["动作","科幻"],"regions":["美国"],"title":"黑客帝国","url":"https:\/\/movie.douban.com\/subject\/1291843\/","release_date":"2000-01-14","actor_count":25,"vote_count":817512,"score":"9.1","actors":["基努·里维斯","劳伦斯·菲什伯恩","凯瑞-安·莫斯","雨果·维文","格洛丽亚·福斯特","乔·潘托里亚诺","马库斯·钟","朱利安·阿拉汗加","马特·多兰","贝琳达·麦克洛里","安东尼雷派克","罗伯特·泰勒","阿达·尼科德莫","罗温·维特","塔玛拉·布朗","纳塔莉·特珍","比尔·扬","克里斯·斯科特","纳许·埃哲顿","张磊","户田惠子","童自荣","保罗·戈达德","沈晓谦","金永钢"],"is_watched":false},{"rating":["9.0","45"],"rank":8,"cover_url":"https://img1.doubanio.com\/view\/photo\/s_ratio_poster\/public\/p1512562287.jpg","is_playable":true,"id":"3742360","types":["剧情","喜剧","动作","西部"],"regions":["中国大陆","中国香港"],"title":"让子弹飞","url":"https:\/\/movie.douban.com\/subject\/3742360\/","release_date":"2010-12-16","actor_count":32,"vote_count":1655649,"score":"9.0","actors":["姜文","葛优","周润发","刘嘉玲","陈坤","张默","姜武","周韵","廖凡","姚橹","邵兵","苗圃","冯小刚","胡军","马珂","白冰","杜奕衡","李静","胡明","危笑","杨奇雨","赵铭","宣晓鸣","绀野千春","郭俊立","马元","姜洪齐","岳红","吴昔果","沙瑀","陈磊","文祥"],"is_watched":false},{"rating":["9.0","45"],"rank":9,"cover_url":"https://img2.doubanio.com\/view\/photo\/s_ratio_poster\/public\/p1910931622.jpg","is_playable":true,"id":"1292000","types":["剧情","动作","悬疑","惊悚"],"regions":["美国","德国","意大利"],"title":"搏击俱乐部","url":"https:\/\/movie.douban.com\/subject\/1292000\/","release_date":"1999-09-10","actor_count":30,"vote_count":826101,"score":"9.0","actors":["爱德华·诺顿","布拉德·皮特","海伦娜·伯翰·卡特","扎克·格雷尼尔","米特·洛夫","杰瑞德·莱托","艾恩·贝利","里奇蒙德·阿奎特","乔治·马奎尔","以斯拉·巴兹顿","Carl Ciarfalio","斯图尔特·布拉姆博格","马特·温斯顿","劳伦·桑切斯","Tyrone R. Livingston","保罗·卡拉夫特斯","Scotch Ellis Loring","Andi Carnick","迈克尔·肖姆斯·维尔斯","Markus Redmond","大卫·安德鲁斯","鲍勃·斯蒂芬森","欧根妮·邦杜兰特","凯文·斯科特·麦克","Bennie Moore","埃文·米兰德","乔伊·比索奈特","Christina Cabot","大卫·李·史密斯","霍特·麦克卡兰尼"],"is_watched":false},{"rating":["8.9","45"],"rank":10,"cover_url":"https://img1.doubanio.com\/view\/photo\/s_ratio_poster\/public\/p1633113220.jpg","is_playable":false,"id":"1300299","types":["剧情","动作","犯罪","悬疑","惊悚"],"regions":["韩国"],"title":"杀人回忆","url":"https:\/\/movie.douban.com\/subject\/1300299\/","release_date":"2003-05-02","actor_count":50,"vote_count":690654,"score":"8.9","actors":["宋康昊","金相庆","金雷夏","宋在浩","边希峰","高瑞熙","柳泰浩","朴努植","朴海日","全美善","徐永嬅","崔钟律","刘承睦","申贤宗","李在应","郑仁仙","吴龙","朴真宇","朴泰京","沈成宝","朴镇宇","廉惠兰","李东勇","赵德济","申文成","孙康国","李大贤","李玉珠","刘仁秀","千明宰","郭秀贞","曹文义","朴贤英","申贤胜","權炳吉","金周灵","金荷景","金熙珍","崔铉基","李江山","孙镇浩","白奉基","刘琴","禹高娜","申云燮","金景来","李勋京","李多一","金景来","崔交植"],"is_watched":false},{"rating":["8.9","45"],"rank":11,"cover_url":"https://img1.doubanio.com\/view\/photo\/s_ratio_poster\/public\/p2004174709.jpg","is_playable":true,"id":"1294639","types":["动作","传记","剧情","历史","战争"],"regions":["美国"],"title":"勇敢的心","url":"https:\/\/movie.douban.com\/subject\/1294639\/","release_date":"1995-05-18","actor_count":24,"vote_count":549708,"score":"8.9","actors":["梅尔·吉布森","苏菲·玛索","布莱恩·考克斯","詹姆斯·科兹莫","辛·劳洛","凯瑟琳·麦克马克","安古斯·麦克菲登","布莱丹·格里森","詹姆斯·霍纳","彼得·穆兰","汤米·弗拉纳根","艾伦·阿姆斯特朗","大卫·奥哈拉","帕特里克·麦高汉","伊安·邦纳","梅丽·卡尔维","史蒂芬·比灵顿","迈克尔·伯恩","亚力克斯·诺顿","杰拉德·迈克索利","詹姆斯·鲁宾逊","辛·麦金利","Donal Gibson","鲁珀特·范西塔特"],"is_watched":false},{"rating":["8.8","45"],"rank":12,"cover_url":"https://img1.doubanio.com\/view\/photo\/s_ratio_poster\/public\/p2219011938.jpg","is_playable":true,"id":"1291543","types":["动作","喜剧","犯罪","奇幻"],"regions":["中国大陆","中国香港"],"title":"功夫","url":"https:\/\/movie.douban.com\/subject\/1291543\/","release_date":"2004-12-23","actor_count":33,"vote_count":1086587,"score":"8.8","actors":["周星驰","元秋","元华","黄圣依","梁小龙","陈国坤","田启文","林子聪","林雪","冯克安","释彦能","冯小刚","袁祥仁","张一白","赵志凌","董志华","何文辉","陈凯师","贾康熙","林子善","任珈锐","王仕颖","冯勉恒","范湉湉","杨能","黄锐民","姜瑰瑾","丁小龙","张明明","钱升玮","林志泰","阮昊天","程守一"],"is_watched":false},{"rating":["8.8","45"],"rank":13,"cover_url":"https://img1.doubanio.com\/view\/photo\/s_ratio_poster\/public\/p2180085848.jpg","is_playable":true,"id":"1652587","types":["动作","科幻","冒险"],"regions":["美国"],"title":"阿凡达","url":"https:\/\/movie.douban.com\/subject\/1652587\/","release_date":"2010-01-04","actor_count":47,"vote_count":1387566,"score":"8.8","actors":["萨姆·沃辛顿","佐伊·索尔达娜","西格妮·韦弗","史蒂芬·朗","米歇尔·罗德里格兹","吉奥瓦尼·瑞比西","乔·大卫·摩尔 ","希·庞德","韦斯·斯塔迪","拉兹·阿隆索","迪利普·劳","马特·杰拉德","肖恩·安东尼·莫兰","杰森·怀特","斯科特·劳伦斯","凯利·基尔戈","詹姆斯·皮特","肖恩·帕特里克·墨菲","彼得·狄龙","凯文·多曼","凯尔森·亨德森","大卫·范·霍恩","雅克布·托毛里","Julene Renee","卢克·霍克","伍迪·舒尔茨","彼得·门萨","伊拉姆·崔","黛布拉·威尔逊","Chris Mala","马修张伯伦","詹姆斯·盖林","拉斯科·阿特金斯","Jørn Benzon","罗文·贝特杰曼","Robert Catto","罗德尼·库克","Nicole Dionne","Anthony Ingruber","蒂姆·卡诺","卡米尔·基南","迪恩·诺斯利","Emma Law","季冠霖","詹姆斯·霍纳","泰瑞·诺塔里","陆建艺"],"is_watched":false},{"rating":["9.1","45"],"rank":14,"cover_url":"https://img9.doubanio.com\/view\/photo\/s_ratio_poster\/public\/p2446408045.jpg","is_playable":true,"id":"1291936","types":["动作","科幻","动画"],"regions":["日本"],"title":"攻壳机动队","url":"https:\/\/movie.douban.com\/subject\/1291936\/","release_date":"1995-11-18","actor_count":16,"vote_count":135609,"score":"9.1","actors":["田中敦子","大塚明夫","山寺宏一","大木民夫","家弓家正","玄田哲章","山内雅人","小川真司","宫本充","小高三良","后藤敦","山路和弘","佐藤政道","Lia Sargent","布莱恩·科兰斯顿","松山鹰志"],"is_watched":false},{"rating":["8.8","45"],"rank":15,"cover_url":"https://img9.doubanio.com\/view\/photo\/s_ratio_poster\/public\/p1596085504.jpg","is_playable":true,"id":"1298070","types":["动作","冒险","奇幻"],"regions":["美国"],"title":"加勒比海盗","url":"https:\/\/movie.douban.com\/subject\/1298070\/","release_date":"2003-11-21","actor_count":34,"vote_count":836229,"score":"8.8","actors":["约翰尼·德普","杰弗里·拉什","奥兰多·布鲁姆","凯拉·奈特莉","杰克·达文波特","乔纳森·普雷斯","李·阿伦伯格","大卫·拜利","马丁·科勒巴","乔迪·卡巴勒罗","劳伦·马赫","安格斯·巴尼特","露欣达·戴泽克","陆建艺","Giles New","小伊萨克·C.辛格尔顿","麦肯锡·克鲁克","Christian Martin","凯文·麦克纳利","瓦妮莎·布兰奇","内杰·亚当森","戴兰·史密斯","盖伊·西纳","达米恩·奥哈尔","David Patykewich","保罗·基斯","罗比·基","卢克·德·沃夫松","佐伊·索尔达娜","乔·格里萨菲","格雷格·埃利斯","特雷瓦·埃迪内","特雷沃·格德达德","杰拉德·J·雷耶斯"],"is_watched":false},{"rating":["8.8","45"],"rank":16,"cover_url":"https://img1.doubanio.com\/view\/photo\/s_ratio_poster\/public\/p2597918718.jpg","is_playable":true,"id":"1295409","types":["剧情","喜剧","动作","犯罪"],"regions":["中国香港"],"title":"纵横四海","url":"https:\/\/movie.douban.com\/subject\/1295409\/","release_date":"1991-02-02","actor_count":13,"vote_count":409672,"score":"8.8","actors":["周润发","张国荣","钟楚红","朱江","曾江","胡枫","唐宁","邓一君","何锦满","韩俊","冯雪瑞","胡大为","唐家辉"],"is_watched":false},{"rating":["8.8","45"],"rank":17,"cover_url":"https://img9.doubanio.com\/view\/photo\/s_ratio_poster\/public\/p1706428744.jpg","is_playable":true,"id":"3395373","types":["剧情","动作","科幻","犯罪","惊悚"],"regions":["美国","英国"],"title":"蝙蝠侠:黑暗骑士崛起","url":"https:\/\/movie.douban.com\/subject\/3395373\/","release_date":"2012-08-27","actor_count":50,"vote_count":701250,"score":"8.8","actors":["克里斯蒂安·贝尔","汤姆·哈迪","安妮·海瑟薇","约瑟夫·高登-莱维特","玛丽昂·歌迪亚","加里·奥德曼","迈克尔·凯恩","摩根·弗里曼","朱诺·坦普尔","乔什·平茨","丹尼尔·逊亚塔","内斯特·卡博内尔","伯恩·戈曼","连姆·尼森","乔伊·金","艾丹·吉伦","基里安·墨菲","乔什·斯图沃特","马修·莫迪恩","本·门德尔森","约翰·诺兰","本·科尼什","克莱尔·茱莉安","伊恩·鲍汉","威廉姆·德瓦内","罗伯特·维斯多姆","弗瑞德里克·林恩","罗伯·布朗","约瑟夫·莱尔·泰勒","艾伦·萨吉尼亚","加里·西弗斯","约翰·麦克米兰","杰克·卡鲁索","迪索·拉莫斯","金锋","英迪娅·沃兹沃思","杰伊·本尼迪克特","托马斯·图尔","阿拉米斯·奈特","特雷弗·怀特","阿隆·阿布布尔","布莱特·卡伦","拉塞尔·巴洛格","艾捷拉·埃文斯","雷吉·李","托马斯·列农","戴斯蒙德·哈灵顿","汤姆·康蒂","大卫·莫纳汉","韦德·威廉姆斯"],"is_watched":false},{"rating":["8.8","45"],"rank":18,"cover_url":"https://img1.doubanio.com\/view\/photo\/s_ratio_poster\/public\/p1800813767.jpg","is_playable":true,"id":"6307447","types":["剧情","动作","西部","冒险"],"regions":["美国"],"title":"被解救的姜戈","url":"https:\/\/movie.douban.com\/subject\/6307447\/","release_date":"2013-05-12","actor_count":38,"vote_count":592591,"score":"8.8","actors":["杰米·福克斯","莱昂纳多·迪卡普里奥","克里斯托弗·瓦尔兹","塞缪尔·杰克逊","凯丽·华盛顿","沃尔顿·戈金斯","丹尼斯·克里斯托弗","乔纳·希尔","詹姆斯·瑞马尔","爱波·塔布琳","弗兰科·内罗","罗伯特·卡拉丁","佐伊·贝尔","昆汀·塔伦蒂诺","布鲁斯·邓恩","基思·卡拉丹","唐·约翰逊","J·D·埃弗摩尔","拉斯·坦布林","劳拉·凯洛蒂","詹姆斯·拉索","奥托·艾森度","瑞克斯·林恩","迈克·康纳·盖尼","耐德·巴拉米","克里斯托弗·贝瑞","唐·司徒奥德","汤姆·沃帕特","妮可·加利西亚","丹妮尔·沃茨","库珀·哈克卡比","凯瑞·西蒙斯","乔恩·阿兹","蒂莫西·皮克勒斯","爱德华·J·克莱尔","莫尼卡·雷内·安德森","里奇·J·拉德纳","克雷格·斯塔克"],"is_watched":false},{"rating":["8.8","45"],"rank":19,"cover_url":"https://img1.doubanio.com\/view\/photo\/s_ratio_poster\/public\/p443461818.jpg","is_playable":true,"id":"1302467","types":["动作","科幻"],"regions":["美国"],"title":"黑客帝国3:矩阵革命","url":"https:\/\/movie.douban.com\/subject\/1302467\/","release_date":"2003-11-05","actor_count":37,"vote_count":436162,"score":"8.8","actors":["基努·里维斯","劳伦斯·菲什伯恩","凯瑞-安·莫斯","雨果·维文","贾达·萍克·史密斯","凯特·宾汉","玛丽·爱丽丝","莫妮卡·贝鲁奇","埃茜·戴维斯","克里斯托弗·卡比","罗伯特·马莫内","罗宾·奈文","吉娜薇·欧瑞丽","诺娜·加耶","纳撒尼尔·利斯","哈里·列尼斯","哈罗德·佩里诺","鲁伯特·雷德","凯文·迈克尔·理查德森","大卫·罗伯茨","布鲁斯·斯宾斯","吉娜·托瑞斯","克莱顿·华生","赫尔穆特·巴凯蒂斯","邹兆龙","乔·曼宁","Tanveer K. Atwal","拉黑·休姆","康奈尔·韦斯特","伯纳德·怀特","朗贝尔·维尔森","安东尼·布兰登·黄","安东尼·泽比","克雷格·沃克","任亚明","户田惠子","蕾切尔·布莱克曼"],"is_watched":false},{"rating":["8.8","45"],"rank":20,"cover_url":"https://img1.doubanio.com\/view\/photo\/s_ratio_poster\/public\/p792223507.jpg","is_playable":true,"id":"1578507","types":["动作","悬疑","惊悚"],"regions":["美国","德国","法国","英国"],"title":"谍影重重3","url":"https:\/\/movie.douban.com\/subject\/1578507\/","release_date":"2007-11-15","actor_count":27,"vote_count":407018,"score":"8.8","actors":["马特·达蒙","朱丽娅·斯蒂尔斯","大卫·斯特雷泽恩","斯科特·格伦","帕迪·康斯戴恩","埃德加·拉米雷兹","阿尔伯特·芬尼","琼·艾伦","克里·约翰逊","丹尼尔·布鲁赫","乔伊·安沙","科林·斯廷顿","丹·弗雷登堡","凯·马丁","迈克尔·怀德曼","马克·莫特拉姆","杰弗里·李·吉布森","布莱恩·考克斯","斯科特·阿金斯","露西·莱曼","汤姆·加洛普","马克·巴泽利","查尔斯·维恩","布兰科·托莫维奇","特雷弗·圣约翰","弗朗卡·波滕特","劳伦斯·波萨"],"is_watched":false}]pprint(html)li=json.loads(html)for dict in li:json.dump(dict,file,ensure_ascii=False)file.write('\r\n')if __name__ == '__main__':spider=DoubanSpider()spider.run('剧情')

python爬虫(正则获取元素)相关推荐

  1. python爬虫——正则获取手机号

    用正则匹配网页手机号 1. 安装re模块.requests库.beautifulsoup4库 cmd → pip install re → 回车 cmd → pip install requests ...

  2. [Python爬虫] Selenium获取百度百科旅游景点的InfoBox消息盒

    前面我讲述过如何通过BeautifulSoup获取维基百科的消息盒,同样可以通过Spider获取网站内容,最近学习了Selenium+Phantomjs后,准备利用它们获取百度百科的旅游景点消息盒(I ...

  3. [python爬虫] Selenium常见元素定位方法和操作的学习介绍(转载)

    转载地址:[python爬虫] Selenium常见元素定位方法和操作的学习介绍 一. 定位元素方法 官网地址:http://selenium-python.readthedocs.org/locat ...

  4. python爬虫(14)获取淘宝MM个人信息及照片(中)

    python爬虫(14)获取淘宝MM个人信息及照片(中) python爬虫(14)获取淘宝MM个人信息及照片(上) python爬虫(14)获取淘宝MM个人信息及照片(下)(windows版本) 在上 ...

  5. Python爬虫实战——获取电影影评

    Python爬虫实战--获取电影影评 前言 第三方库的安装 示例代码 效果演示 结尾 前言 使用Python爬取指定电影的影评, 注意:本文仅用于学习交流,禁止用于盈利或侵权行为. 操作系统:wind ...

  6. python爬虫(14)获取淘宝MM个人信息及照片(上)

    python爬虫(14)获取淘宝MM个人信息及照片(上) python爬虫(14)获取淘宝MM个人信息及照片(中) python爬虫(14)获取淘宝MM个人信息及照片(下)(windows版本) 网上 ...

  7. Python+爬虫技术获取斗鱼直播图片(整理)

    核心内容: 1.爬虫的基本原理 2.利用Python爬取数据的方法(使用urllib爬取数据) 3.从斗鱼直播平台爬取图片 最近因为工作的原因,要利用爬虫的相关技术,获取html网页相关的数据,特意总 ...

  8. Python爬虫之获取淘宝商品数据

    爬取淘宝信息数据 首先需要先导入webdriver from selenium import webdriver webdriver支持主流的浏览器,比如说:谷歌浏览器.火狐浏览器.IE浏览器等等 然 ...

  9. Python 爬虫:获取 JS 动态内容——应用宝搜索应用

      本内容主要介绍如何获取网页中 JS 动态生成的内容. 文章目录 1.1 Ajax 异步加载生成网页内容 1.2 从网页响应中找到 JS 脚本返回的数据 1.2.1 找到 JS 请求的数据接口 1. ...

  10. (干货)你知道python爬虫定位网页元素有几种方式嘛,今天带你一一了解。

    本文的文字及图片来源于网络,仅供学习.交流使用,不具有任何商业用途,版权归原作者所有,如有问题请及时联系我们以作处理 以下文章来源于腾讯云 作者:拓荒者 ( 想要学习Python?Python学习交流 ...

最新文章

  1. BZOJ1566:[NOI2009]管道取珠——题解
  2. linux 内核 编译详解
  3. Kerberos 原理简述
  4. C语言优先级——取反和移位
  5. 创建vue项目(一)搭建vue-cli、项目文件介绍、简单配置
  6. 最长升序子串1231
  7. 设计一个类代表二维空间的一个圆。_平面设计基础——点、线、面
  8. HttpClient4.5 简单入门实例(一)
  9. full join 和full outer join_多表关联:公式展开、join、过滤条件的顺序
  10. php后端路由,laravel实现前后台路由分离的方法
  11. JavaScript获取java变量值
  12. python queue join,python3多线程通信方式,主要理解队列的join()和task_done()方法
  13. spss 安装包以及许可证
  14. linux dosbox使用教程,dosbox安装及汇编教程 dosbox的常用快捷键
  15. 阅读《资本论》简单思考和笔记
  16. JS:Falsy Bouncer(过滤数组假值)
  17. 看网易的lofter,预测轻博客的未来
  18. 真香!红色警戒游戏源代码被开源了!
  19. mac上metersphere本地开发环境搭建
  20. 使用malloc为指针分配内存空间

热门文章

  1. 进一寸有进一寸的欢喜,谈谈如何优化 Milvus 数据库的向量查询功能
  2. 笔记本电脑未监测到电池分享一下技巧
  3. 我们都是小清新,学习——So easy
  4. 查询亿级数据毫秒级返回!牛逼哄哄的ElasticSearch是如何做到的?
  5. 苹果推出智能音箱Homepod
  6. 500个爆文标题_超级标题库,史上最全爆文标题套路都在这里了,内容宝文章
  7. Java高并发多线程
  8. 无人机数据处理—Pix4Dmapper解析
  9. 华为上半年手机销量_2019上半年手机销量排行榜出炉,华为一骑绝尘,魅族联想上榜...
  10. Java-集合、泛型