Python captures watercress pictures and automatically saves sample learning

Environment Python 2.7.6,BS4, which can be run in PowerShell or at the command line. Make sure that the BS module is installed

The code is as follows:

#-*-Coding:utf8-*-
# 2013.12.36 19:41 wnlo-c209
# Grab a picture of dbmei.com.

From BS4 import BeautifulSoup
Import OS, sys, URLLIB2

# Create a folder, just learned yesterday
Path = OS.GETCWD () # Gets the directory where this script is located
New_path = Os.path.join (path,u ' watercress sister ')
If not Os.path.isdir (New_path):
Os.mkdir (New_path)

def page_loop (page=0):
url = ' http://www.dbmeizi.com/?p=%s '% page
Content = Urllib2.urlopen (URL)

Soup = beautifulsoup (content)

My_girl = Soup.find_all (' img ')

# Add end detection, write bad ....
If My_girl ==[]:
Print U ' has been completely crawled '
Sys.exit (0)

Print u ' start crawl '
For girl in My_girl:
link = girl.get (' src ')
Flink = ' http://www.dbmeizi.com/' + link

Print Flink
Content2 = Urllib2.urlopen (Flink). Read ()
with open (U ' watercress sister ' + '/' +flink[-11:], ' WB ') as code: #在OSC上现学的
Code.write (Content2)
page = Int (page) + 1
Print U ' start scratching and removing a page '
print ' The%s page '% page
Page_loop (page)

Page_loop ().

