Capture pictures of sisters and capture sisters

Capture pictures of sisters and capture sisters

Import requests

From bs4 import BeautifulSoup

Import OS

 

Class mzitu ():

 

Def requst (self, url): # define the function for obtaining web pages

Headers = {'user-agent': "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) chrome/57.0.2987.20.safari/537.36 "} # simulate a browser to prevent anti-crawler attacks

Content = requests. get (url, headers = headers) # obtain webpage content

Return content

 

Def all_url (self, url): # define the function for obtaining the main webpage

Html = self. requst (url) # obtain all content of the main page

All_a = BeautifulSoup (html. text, 'lxml'). find ('div ', class _ = 'all'). find_all ('A') # parse webpages through beautifulsoup. Find the content of all images on the home page

Print (len (all_a) # print the total number of images

For a in all_a: # traverse all image links

Title = a. get_text () # assign the text in image attribute a to the title

Print (U' start to save: ', title)

Path = str (title). replace ("? ", '_') # Add? Replace with null

Self. mkdir (path) Stores slices by path

Href = a ['href '] # obtain the content link of each image.

Self.html (href)

Def html (self, href): # define the function to get the link of each page of each set of images

Html = self. requst (href) # obtain the webpage content of an image

# Because a set of images has multiple pages, each page has an image. Therefore, we need to analyze the links of each page of each set of images.

Max_span = BeautifulSoup (html. text, 'lxml '). find ('div ', class _ = 'pagenavi '). find_all ('span ') [-2]. get_text () # parse to get all the pages of each set of images

For page in range (1, int (max_span) + 1): # traverse pages

Page_url = href + '/' + str (page) # obtain the link of the image on each page, that is, add the number of songs to the link of each set of images

Self. img (page_url)

Def img (self, page_url): # obtain the image details on each page.

Img_html = self. requst (page_url) # obtain all information on each page

Img_url = BeautifulSoup (img_html.text, 'lxml '). find ('div ', class _ = 'main-image '). find ('img ') ['src'] # parse the page content

Self. save (img_url) # save the image

Def save (self, img_url): # defines the function for saving images.

Name = img_url [-9:-4] # image name

Img = self. requst (img_url) # obtain the image content

F = open ("E :\\ Python \ Pythonprogram \ 图 \" +name}'.jpg ',' AB ') # open the Save path

F. write (img. content) saves the image content

F. close () close

Def mkdir (self, path): # Save the file in the path

Path = path. strip ()

IsExists = OS. path. join ("E: \ Python \ Pythonprogram \ % s" % path) whether this path exists

If not isExists:

Print (u'create a folder named ', path, U ')

OS. makedirs (OS. path. join ("E: \ Python \ Pythonprogram \ % s" % path) # create a path if it does not exist

OS. chdir (OS. path. join ("E: \ Python \ Pythonprogram \ % s" % path) # Save the image to the path

Return True

Else:

Print (U' the folder named ', path, U' already exists ')

Return False

 

Mzitu = mzitu () instantiate the sister chart class

Mzitu. all_url ('HTTP: // www.mzitu.com/all') # enter the parameter URL