本案例介紹從JavaScript中采集加載的數據。更多內容請參考:Python學習指南

#-*-  coding:utf-8 -*-
import requests
import re
import time
import json

#數據下載器
class HtmlDownloader(object):
    def download(self, url, params=None):
        if url is None:
            return None
        user_agent = ‘Mozilla/5.0 (Windows NT 6.1; WOW64; rv:48.0) Gecko/20100101 Firefox/48.0‘
        headers = {‘User-Agent‘:user_agent}
        if params is None:
            r = requests.get(url, headers = headers)
        else:
            r = requests.get(url, headers = headers, params = params)
        if r.status_code == 200:
            r.encoding = ‘utf-8‘
            return r.text
        return None

#數據存儲器
class HtmlParser(object):

    #從選購電影頁面中解析出所有電影信息，組成一個list
    def parser_url(self, page_url, response):
        pattern = re.compile(r‘(http://movie.mtime.com/(\d+)/)‘)
        urls = pattern.findall(response)
        if urls != None:
            #將urls去重
            return list(set(urls))
        else:
            return None

    #解析正在上映的電影
    def __parser_release(self, page_url, value):
        ‘‘‘
            解析已經上映的電影
            :param page_url：電影鏈接
            :param value: json數據
            :return
        ‘‘‘
        try:
            isRelease = 1
            movieRating = value.get(‘value‘).get(‘movieRating‘)
            boxOffice = value.get(‘value‘).get(‘boxOffice‘)
            movieTitle = value.get(‘value‘).get(‘movieTitle‘)
            
            RPictureFinal = movieRating.get(‘RPictureFinal‘)
            RStoryFinal = movieRating.get(‘RStoryFinal‘)
            RDirectorFinal = movieRating.get(‘RDirectorFinal‘)
            ROtherFinal = movieRating.get(‘ROtherFinal‘)
            RatingFinal = movieRating.get(‘RatingFinal‘)

            MovieId = movieRating.get("MovieId")
            UserCount = movieRating.get("Usercount")
            AttitudeCount = movieRating.get("AttitudeCount")

            TotalBoxOffice = boxOffice.get("TotalBoxOffice")
            TotalBoxOfficeUnit = boxOffice.get("TotalBoxOfficeUnit")
            TodayBoxOffice = boxOffice.get("TodayBoxOffice")
            TodayBoxOfficeUnit = boxOffice.get("TodayBoxOfficeUnit")

            ShowDays = boxOffice.get(‘ShowDays‘)
            try:
                Rank = boxOffice.get(‘Rank‘)
            except Exception,e:
                Rank = 0
            #返回所提取的內容
            return (MovieId, movieTitle, RatingFinal, ROtherFinal, RPictureFinal, RDirectorFinal, RStoryFinal, UserCount, AttitudeCount, TotalBoxOffice+TotalBoxOfficeUnit, TodayBoxOffice+TodayBoxOfficeUnit, Rank, ShowDays, isRelease)
        except Exception, e:
            print e, page_url, value
            return None

    #解析未上映的電影
    def __parser_no_release(self, page_url, value, isRelease=0):
        ‘‘‘
            解析未上映的電影信息
            :param page_url
            :param value
            : return
        ‘‘‘
        try:
            movieRating = value.get(‘value‘).get(‘movieRating‘)
            movieTitle = value.get(‘value‘).get(‘movieTitle‘)
            
            RPictureFinal = movieRating.get(‘RPictureFinal‘)
            RStoryFinal = movieRating.get(‘RStoryFinal‘)
            RDirectorFinal = movieRating.get(‘RDirectorFinal‘)
            ROtherFinal = movieRating.get(‘ROtherFinal‘)
            RatingFinal = movieRating.get(‘RatingFinal‘)

            MovieId = movieRating.get("MovieId")
            UserCount = movieRating.get("Usercount")
            AttitudeCount = movieRating.get("AttitudeCount")

            try:
                Rank = value.get(‘value‘).get(‘hotValue‘).get(‘Ranking‘)
            except Exception,e:
                Rank = 0
            #返回所提取的內容
            return (MovieId, movieTitle, RatingFinal, ROtherFinal, RPictureFinal, RDirectorFinal, RStoryFinal, UserCount, AttitudeCount, u‘無‘, u‘無‘, Rank, 0, isRelease)
        except Exception, e:
            print e, page_url, value
            return None

    #解析電影中的json信息
    def parser_json(self, page_url, response):
        """
            解析響應
            :param response
            :return
        """
        #將"="和";"之間的內容提取出來
        pattern = re.compile(r‘=(.*?);‘)
        result = pattern.findall(response)[0]
        if result != None:
            #json模塊加載字符串
            value = json.loads(result)
            # print(result)
            try:
                isRelease = value.get(‘value‘).get(‘isRelease‘)
            except Exception, e:
                print e
                return None
            if isRelease:
                ‘‘‘
                    isRelease:0 很長時間都不會上映的電影；1 已經上映的電影； 2 即將上映的電影
                ‘‘‘
                if value.get(‘value‘).get(‘hotValue‘) == None:
                    #解析正在上映的電影
                    # print(self.__parser_release(page_url, value))
                    return self.__parser_release(page_url, value)
                else:
                    #解析即將上映的電影
                    # print(self.__parser_no_release(page_url, value, isRelease = 2))
                    return self.__parser_no_release(page_url, value, isRelease = 2)
            else:
                #解析還有很長時間才能上映的電影
                return self.__parser_no_release(page_url, value)

#數據存儲器
#數據存儲器將返回的數據插入mysql數據庫中，主要包括建表，插入和關閉數據庫等操作，表中設置了15個字段，用來存儲電影信息，代碼如下：  
#這裏以後補充

class SpiderMain(object):
    def __init__(self):
        self.downloader = HtmlDownloader()
        self.parser = HtmlParser()

    def crawl(self, root_url):
        content = self.downloader.download(root_url)
        urls = self.parser.parser_url(root_url, content)

        #構造一個活的評分和票房鏈接
        for url in urls:
            try:
                t = time.strftime("%Y%m%d%H%M%S3282", time.localtime())
                param = {
                    ‘Ajax_CallBack‘:‘true‘,
                    ‘Ajax_CallBackType‘: ‘Mtime.Library.Services‘,
                    ‘Ajax_CallBackMethod‘: ‘GetMovieOverviewRating‘,
                    ‘Ajax_CallBackArgument0‘ : ‘%s‘%(url[1]),
                    ‘Ajax_RequestUrl‘ : ‘%s‘%(url[0]),
                    ‘Ajax_CrossDomain‘ : ‘1‘,
                    ‘t‘ : ‘%s‘%t
                }
                rank_url = ‘http://service.library.mtime.com/Movie.api?‘
                rank_content = self.downloader.download(rank_url, param)
                data = self.parser.parser_json(rank_url, rank_content)

                self.output.output_end()
            except Exception, e:
                print("Crawl failed")

if __name__ == ‘__main__‘:
    spier = SpiderMain()
    spier.crawl(‘http://theater.mtime.com/China_Jiangsu_Province_Nanjing/‘)
 

Python爬蟲(二十)_動態爬取影評信息