Python downloading JavaScript Effects

Python downloading JavaScript Effects

This article will share with you the code for capturing the JS script special effect template of the lazy library by using Python crawlers. It is implemented using a third-party library gevent. If you need it, you can refer to it.

This is a simple Python script. It is mainly used to download JavaScript special effect templates from the lazy library. The gevent third-party library is used in the script and needs to be installed first.

?

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77

#! /Usr/bin/python #-*-Coding: UTF-8 -*-   Import urllib, OS, sys Import gevent, re From gevent import monkey From bs4 import BeautifulSoup Gevent. monkey. patch_socket ()   ''' Description: The Python crawler crawls the JS Script Template of the lazy Image Library. Author: admin Create-Date: 2015-05-25 Version: 1.0 '''   HTTP_URL = 'HTTP: // www.lanw.uku.com % s' DOWNLOAD_URL = HTTP_URL [:-2] + '/js/d % szip' Reg = R' \ d {1,} \. +'   Def encode (text ): Return text. encode ("utf8 ")   Def createDirectory (curPath ): MyPath = OS. path. join (getSubDirectory (), u 'js code template ') If not OS. path. exists (myPath ): OS. mkdir (myPath) Return OS. path. join (myPath, curPath)   Def getSubDirectory (): Return OS. getcwd ()   Def schedule (a, B, c ): Per = 100.0 * a * B/c If per> 100: Per = 100. Sys. stdout. write ('%. 1f % \ R' % per) Sys. stdout. flush ()   Def geturllist (url ): Url_list = {} Html = urllib. urlopen (url) Content = html. read () Html. close () # Use BeautifulSoup for parsing DecodeHtml = BeautifulSoup (content) Try: ATags = decodeHtml. find_all ('div ', {'class': 'LIST-pngjs'}) [0]. find_all ('A ') Failed t IndexError, e: Print e ATags = None # Obtain the link address and title If aTags is not None: For a_tag in aTags: Url_list [HTTP_URL % a_tag.get ('href ')] = a_tag.get_text () Return url_list   Def download (down_url ): Try: M = re. search (reg, down_url [0]) Name = DOWNLOAD_URL % m. group (0) Urllib. urlretrieve (name, createDirectory (down_url [1] + name [-4:]), schedule) Except t Exception, e: Print e. message   Def getpageurl (xUrl ): # List page Loop Return [xUrl % page for page in xrange (1, 49)]   If _ name _ = '_ main __': Jobs = [] Pageurl = getpageurl ('HTTP: // www.lanw.uku.com/js/p?s.html ') # Crawling all links For I in pageurl: For k in geturllist (I). items (): Jobs. append (gevent. spawn (download, k )) Gevent. joinall (jobs)

The above is all the content of this article. I hope you will like it.