Last active
December 20, 2015 07:39
-
-
Save zippera/6094689 to your computer and use it in GitHub Desktop.
好图爬虫
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from urllib2 import urlopen, URLError | |
| from urllib import urlretrieve | |
| import threading | |
| import re | |
| import os | |
| downroot = r'D:\luguan' | |
| p1 = re.compile(r'src="img.+jpg') | |
| p2 = re.compile(r'\d{1,}\.jpg') | |
| prefix = 'http://www.lu-guan.com/xxoo/' | |
| def clean_dir(top): | |
| for root, dirs, files in os.walk(top, topdown=False): | |
| for name in files: | |
| os.remove(os.path.join(root, name)) | |
| for name in dirs: | |
| os.rmdir(os.path.join(root, name)) | |
| def down_pics(): | |
| print('start downloading') | |
| todown = range(1, 31) | |
| logfile = os.path.join(downroot, 'log') | |
| if os.path.exists(logfile): | |
| log = open(logfile, 'r+') | |
| downed = log.read().split(' ') | |
| else: | |
| log = open(logfile, 'w') | |
| downed = [] | |
| for i in range(1, 101): | |
| if str(i) in downed: | |
| continue; | |
| url = prefix + ('%03d' % i) + '.html' | |
| print 'downloading %s' % url | |
| try: | |
| if down_one_url(url, i) == 404: | |
| break; | |
| except: | |
| print 'error occured during downloading %s' % url | |
| continue | |
| downed.append(str(i)) | |
| print '%d completed' % i | |
| content = ' '.join(downed) | |
| log.write(content) | |
| log.close() | |
| print('finished!') | |
| def down_one_url(url, index): | |
| folder = downroot + '\\' + ('%03d' % index) | |
| if not os.path.exists(folder): | |
| os.makedirs(folder) | |
| else: | |
| clean_dir(folder) | |
| try: | |
| data = urlopen(url).read(); | |
| except URLError, e: | |
| if e.code == 404: | |
| return 404 | |
| piclist = p1.findall(data) | |
| task_threads=[] | |
| for item in piclist: | |
| pic_path = prefix + item[5:] | |
| filepath = downroot + '\\%03d' % index + '\\' + p2.findall(item)[0] | |
| t = threading.Thread(target = urlretrieve, args = (pic_path, filepath)) | |
| task_threads.append(t) | |
| for task in task_threads: | |
| task.start() | |
| for task in task_threads: | |
| task.join(300) | |
| return 0 | |
| if __name__ == '__main__': | |
| if not os.path.exists(downroot): | |
| os.mkdir(downroot) | |
| down_pics(); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment