Tumblr整站图片下载

#! /usr/bin/python3
import os, sys, urllib
from urllib import request, parse
from bs4 import BeautifulSoup

def basename(url):
    return os.path.basename(parse.urlparse(url).path)

def download(url, file):
    '''download file'''
    colWidth = 50
    __perLen = 0
    def reporthook(a, b, c):
        nonlocal __perLen
        per = (100*a*b)/c
        if per>100: per=100
        realCol = int(per/100 * colWidth)
        down = '='*(realCol-1)
        undown = ' '*(colWidth-realCol)
        process = '['+down+'>'+undown+']'
        per = '{:.2f}%'.format(per)
        print('\b'*__perLen, per+' '+process, end=' ', flush=True)
        __perLen = len(per)+len(process)+4

    print('Downloading URL File:\t%s' % (url))
    urllib.request.urlretrieve(url, file, reporthook)
    print('Downloaded!')

def downImages(post):
    for image in post.find_all('img'):
        filename = basename(image['src'])
        if(os.path.exists(filename)):
            print(filename+' exists!')
            continue
        download(image['src'], filename)

def spider(url):
    global start
    print("It has ready to parse URL: "+url)
    html = BeautifulSoup( request.urlopen(url).read() )
    for post in html.select(".post"):
        iframe = post.find('iframe')
        if(iframe):
            if 'photoset' not in iframe['class']: continue #! True Video Post
            iframe = BeautifulSoup( request.urlopen(iframe['src']).read() )
            downImages(iframe)
        else: downImages(post)

    start += 1
    spider('%s/page/%d' % (URL, start))

if(len(sys.argv) <= 1): sys.exit('no tumblr blog url')
_, URL, *start = sys.argv
start = int( start[0] if len(start)>0 else 1 )
spider('%s/page/%d' % (URL, start))

Python3 Spider.py http://triketora.tumblr.com/

Python3 Spider.py http://triketora.tumblr.com/ 30