# 导入库from selenium import webdriver

# 浏览驱动器路径chromedriver = 'E:/software/chromedriver_win32/chromedriver.exe'driver = webdriver.Chrome(chromedriver)

driver.get("此处填写网址")

driver.find_element_by_xpath('//*[@id="comments"]/div[{}]/div[2]/p/span')

# 新建文件夹及文件basePathDirectory = "Hudong_Coding"if not os.path.exists(basePathDirectory):        os.makedirs(basePathDirectory)baiduFile = os.path.join(basePathDirectory, "hudongSpider.txt")# 若文件不存在则新建，若存在则追加写入if not os.path.exists(baiduFile):        info = codecs.open(baiduFile, 'w', 'utf-8')else:        info = codecs.open(baiduFile, 'a', 'utf-8')

info.writelines(elem.text + '/r/n')

# -*- coding: utf-8 -*-# !/usr/bin/env pythonimport osimport codecsfrom selenium import webdriver # 获取摘要信息def getFilmReview():    try:        # 新建文件夹及文件        basePathDirectory = "DouBan_FilmReview"        if not os.path.exists(basePathDirectory):            os.makedirs(basePathDirectory)        baiduFile = os.path.join(basePathDirectory, "DouBan_FilmReviews.txt")        # 若文件不存在则新建，若存在则追加写入        if not os.path.exists(baiduFile):            info = codecs.open(baiduFile, 'w', 'utf-8')        else:            info = codecs.open(baiduFile, 'a', 'utf-8')         # 浏览驱动器路径        chromedriver = 'E:/software/chromedriver_win32/chromedriver.exe'        os.environ["webdriver.chrome.driver"] = chromedriver        driver = webdriver.Chrome(chromedriver)        # 打开网页        for k in range(15000):  # 大约有15000页            k = k + 1            g = 2 * k            driver.get("https://movie.douban.com/subject/34841067/comments?start={}".format(g))            try:                # 自动搜索                for i in range(21):                    elem = driver.find_element_by_xpath('//*[@id="comments"]/div[{}]/div[2]/p/span'.format(i+1))                    print(elem.text)                    info.writelines(elem.text + '/r/n')            except:                pass     except Exception as e:        print('Error:', e)     finally:        print('/n')        driver.close() # 主函数def main():    print('开始爬取')    getFilmReview()    print('结束爬取') if __name__ == '__main__':    main()

# -*- coding: utf-8 -*-# !/usr/bin/env python import jieba                #中文分词import wordcloud            #绘制词云 # 显示数据 f = open('E:/software/pythonProject/DouBan_FilmReview/DouBan_FilmReviews.txt', encoding='utf-8') txt = f.read()txt_list = jieba.lcut(txt)# print(txt_list)string = ' '.join((txt_list))print(string) # 很据得到的弹幕数据绘制词云图# mk = imageio.imread(r'图片路径') w = wordcloud.WordCloud(width=1000,                        height=700,                        background_color='white',                        font_path='C:/Windows/Fonts/simsun.ttc',                        #mask=mk,                        scale=15,                        stopwords={' '},                        contour_width=5,                        contour_color='red'                        ) w.generate(string)w.to_file('DouBan_FilmReviews.png')

# -*- coding: utf-8 -*-# !/usr/bin/env pythonimport osimport timeimport datetimeimport requests class PF(object):    def __init__(self):        self.url = 'https://piaofang.maoyan.com/dashboard-ajax?orderType=0&uuid=173d6dd20a2c8-0559692f1032d2-393e5b09-1fa400-173d6dd20a2c8&riskLevel=71&optimusCode=10'        self.headers = {            "Referer": "https://piaofang.maoyan.com/dashboard",            "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36",        }     def main(self):        while True:            # 需在dos命令下运行此文件，才能清屏            os.system('cls')            result_json = self.get_parse()            if not result_json:                break            results = self.parse(result_json)            # 获取时间            calendar = result_json['calendar']['serverTimestamp']            t = calendar.split('.')[0].split('T')            t = t[0] + " " + (datetime.datetime.strptime(t[1], "%H:%M:%S") + datetime.timedelta(hours=8)).strftime("%H:%M:%S")            print('北京时间:', t)            x_line = '-' * 155            # 总票房            total_box = result_json['movieList']['data']['nationBoxInfo']['nationBoxSplitUnit']['num']            # 总票房单位            total_box_unit = result_json['movieList']['data']['nationBoxInfo']['nationBoxSplitUnit']['unit']            print(f"今日总票房: {total_box} {total_box_unit}", end=f'/n{x_line}/n')            print('电影名称'.ljust(14), '综合票房'.ljust(11), '票房占比'.ljust(13), '场均上座率'.ljust(11), '场均人次'.ljust(11),'排片场次'.ljust(12),'排片占比'.ljust(12), '累积总票房'.ljust(11), '上映天数', sep='/t', end=f'/n{x_line}/n')            for result in results:                print(                    result['movieName'][:10].ljust(9),  # 电影名称                    result['boxSplitUnit'][:8].rjust(10),  # 综合票房                    result['boxRate'][:8].rjust(13),  # 票房占比                    result['avgSeatView'][:8].rjust(13),  # 场均上座率                    result['avgShowView'][:8].rjust(13),  # 场均人次                    result['showCount'][:8].rjust(13),  # '排片场次'                    result['showCountRate'][:8].rjust(13),  # 排片占比                    result['sumBoxDesc'][:8].rjust(13),  # 累积总票房                    result['releaseInfo'][:8].rjust(13),  # 上映信息                    sep='/t', end='/n/n'                )                break            time.sleep(4)     def get_parse(self):        try:            response = requests.get(self.url, headers=self.headers)            if response.status_code == 200:                return response.json()        except requests.ConnectionError as e:            print("ERROR:", e)            return None     def parse(self, result_json):        if result_json:            movies = result_json['movieList']['data']['list']            # 场均上座率, 场均人次, 票房占比, 电影名称,            # 上映信息（上映天数）, 排片场次, 排片占比, 综合票房,累积总票房            ticks = ['avgSeatView', 'avgShowView', 'boxRate', 'movieName',                     'releaseInfo', 'showCount', 'showCountRate', 'boxSplitUnit', 'sumBoxDesc']            for movie in movies:                self.piaofang = {}                for tick in ticks:                    # 数字和单位分开需要join                    if tick == 'boxSplitUnit':                        movie[tick] = ''.join([str(i) for i in movie[tick].values()])                    # 多层字典嵌套                    if tick == 'movieName' or tick == 'releaseInfo':                        movie[tick] = movie['movieInfo'][tick]                    if movie[tick] == '':                        movie[tick] = '此项数据为空'                    self.piaofang[tick] = str(movie[tick])                yield self.piaofang  if __name__ == '__main__':    while True:        pf = PF()        pf.main()

# -*- coding: utf-8 -*-# !/usr/bin/env pythonimport requestsfrom bs4 import BeautifulSoupimport refrom PIL import Image def get_data(url):    # 请求网页    resp = requests.get(url)    # headers 参数确定    headers = {        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.122 Safari/537.36'    }        # 对于获取到的 HTML 二进制文件进行 'utf-8' 转码成字符串文件    html = resp.content.decode('utf-8')    # BeautifulSoup缩小查找范围    soup = BeautifulSoup(html, 'html.parser')    # 获取 <a> 的超链接    for link in soup.find_all('a'):        a = link.get('href')        if type(a) == str:            b = re.findall('(.*?)jpg', a)            try:                print(b[0]+'jpg')                img_urls = b[0] + '.jpg'                # 保存数据                for img_url in img_urls:                    # 发送图片 URL 请求                    image = requests.get(img_url, headers=headers).content                    # 保存数据                    with open(r'E:/IMAGES/' + image, 'wb') as img_file:                        img_file.write(image)            except:                pass        else:            pass # 爬取目标网页if __name__ == '__main__':    get_data('https://www.1905.com/newgallery/hdpic/1495100.shtml')