Python脚本问题

时间:2016-11-15 05:36:33

标签: python

很抱歉,如果我以前问了类似的问题。我有一个python脚本用于从网站iFunny抓取图像和GIF。问题是,我以前从未使用过python,所以我几乎不知道它是如何工作的。我扔了一些代码(你会在其中看到评论)从ifunny下载gifs,但现在它不再有用了。而不是gif,我只是得到一个图像缩略图。谁可以在这里体验python帮助我改进这个脚本,以便它可以从ifunny可靠地下载图像和GIF?任何帮助都会非常感激!

代码:

import os
import time
from html.parser import HTMLParser
import urllib.request

#todo: char support for Windows
#deal with triple backslash filter
#recursive parser option


class LiteScraper(HTMLParser):
    def __init__(self):
        HTMLParser.__init__(self)
        self.lastStartTag="No-Tag"
        self.lastAttributes=[]
        self.lastImgUrl=""
        self.Data=[]
        self.acceptedTags=["div","p","h","h1","h2","h3","h4","h5","h6","ul","li","a","img"]
        self.counter=0
        self.url=""


        self.SAVE_DIR="" #/Users/stjepanbrkic/Desktop/temp
        self.Headers=["User-Agent","Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.36"]

    def handle_starttag(self,tag,attrs):
        #print("Encountered a START tag:",tag)
        self.lastStartTag=tag
        self.lastAttributes=attrs #unnecesarry, might come in hany

        if self.lastStartTag=="img":
            attrs=self.lastAttributes

            for attribute in attrs:
                if attribute[0]=="src":
                    self.lastImgUrl=attribute[1]
                    print(attribute[1])

                    #Allow GIF from iFunny to download
                    for attribute in attrs:
                        if attribute[0]=="data-gif":
                            self.lastImgUrl=attribute[1]
                            print(attribute[1])
                            #End Gif Code

            self.handle_picture(self.lastImgUrl)

    def handle_endtag(self,tag):
        #print("Encountered a END tag:",tag)
        pass

    def handle_data(self,data):
        data=data.replace("\n"," ")
        data=data.replace("\t"," ")
        data=data.replace("\r"," ")
        if self.lastStartTag in self.acceptedTags:
            if not data.isspace():
                print("Encountered some data:",data)
                self.Data.append(data)

        else:
            print("Encountered filtered data.") #Debug

    def handle_picture(self,url):
        print("Bumped into a picture. Downloading it now.")
        self.counter+=1
        if url[:2]=="//":
            url="http:"+url

        extension=url.split(".")
        extension="."+extension[-1]

        try:
            req=urllib.request.Request(url)
            req.add_header(self.Headers[0],self.Headers[1])
            response=urllib.request.urlopen(req,timeout=10)
            picdata=response.read()
            file=open(self.SAVE_DIR+"/pics/"+str(self.counter)+extension,"wb")
            file.write(picdata)
            file.close()
        except Exception as e:
            print("Something went wrong, sorry.")


    def start(self,url):
        self.url=url
        self.checkSaveDir()

        try: #wrapped in exception - if there is a problem with url/server
            req=urllib.request.Request(url)
            req.add_header(self.Headers[0],self.Headers[1])
            response=urllib.request.urlopen(req,timeout=10)
            siteData=response.read().decode("utf-8")
            self.feed(siteData)
        except Exception as e:
            print(e)

        self.__init__()  #resets the parser/scraper for serial parsing/scraping
        print("Done!")

    def checkSaveDir(self):
        #----windows support
        if os.name=="nt":
            container="\ "
            path=os.path.normpath(__file__)
            path=path.split(container[0])
            path=container[0].join(path[:len(path)-1])
            path=path.split(container[0])
            path="/".join(path)
        #no more windows support! :P
        #for some reason, os.normpath returns path with backslashes
        #on windows, so they had to be supstituted with fowardslashes.

        else:
            path=os.path.normpath(__file__)
            path=path.split("/")
            path="/".join(path[:len(path)-1])

        foldername=self.url[7:]
        foldername=foldername.split("/")[0]

        extension=time.strftime("iFunny")+"-"+time.strftime("%d-%m-%Y") + "-" + time.strftime("%Hh%Mm%Ss")

        self.SAVE_DIR=path+"/"+foldername+"-"+extension


        if not os.path.exists(self.SAVE_DIR):
            os.makedirs(self.SAVE_DIR)

        if not os.path.exists(self.SAVE_DIR+"/pics"):
            os.makedirs(self.SAVE_DIR+"/pics")

        print(self.SAVE_DIR)

我正在用它来运行它:

from LiteScraper import LiteScraper
scraper=LiteScraper()
scraper.start("https://ifunny.co/feeds/shuffle")

0 个答案:

没有答案