Python interface Automation Test 18: Crawling pictures using the BS4 framework

 # crawl Picture 
 # target site: http://699pic.com/sousuo-218808-13-1.html 
 Import requests 
 from BS4 import BeautifulSoup 
 Import os 
 r = requests.get (' http://699pic.com/sousuo-218808-13-1.html ') 
 
 # r.content # returns a byte stream 
 
 Soup = BeautifulSoup (r.content, ' Html.parser ') # with the HTML parser, find r.content 
 
 # tu = Soup.find_all (' img ') # Find all the tags named "I  MG "Object 
 Tu = Soup.find_all (class_=" lazy ") # Find all tags named" class_= "Lazy" "Object 
 
 
 for i in Tu: 
 # print (i) 
 #  
 Print (i[' data-original ') # get all URL addresses 
 
 # Crawl single picture 
 URL = ' Http://img95.699pic.com/photo/50061/5608.jpg_wh 300.jpg ' 
 r = requests.get (URL) 
 F = open (' 123.jpg ', ' WB ') # Opens a file named 123.jpg as a binary write (suffix can be arbitrarily changed) 
 F.write ( R.content) # Writes a stream of R bytes to a file 
 F.close () # Close File 

# Bulk Write:

# Create a path,  create a folder named "Tupian"
Curpath = Os.path.dirname (Os.path.dirname (Os.path.realpath (__file__)))
Tupian = Os.path.join (Curpath, ' Tupian ')
If not os.path.exists (Tupian):  # Determine if the folder named "Tupian" is not present
    Os.mkdir (Tupian)        # does not exist, then a folder named "Tupian" is created
# Write pictures in batches and save
For I in Tu:
    Try
        Jpg_url = i[' data-original ']    # The address of the picture to get
        name = i[' Alt ']
        R = Requests.get (Jpg_url)
        # Write the content and put it in the Tupian folder
        f = open (Os.path.join (Tupian, '%s.jpg '%name), ' WB ')
        F.write (r.content)
        F.close ()
    Except
        Pass

Python interface Automation Test 18: Crawling pictures using the BS4 framework