Python crawlers to crawl pure girl pictures

Before running the code, you need to install BeautifulSoup, requests, os library.

From bs4 import BeautifulSoup

Import requests

Import time

Import os

Def get_html(url):

    Try:

        Response=requests.get(url)

        Response.encoding='gb2312'

        If response.status_code==200:

            Print('Successfully connected! URL is '+url)

            Return response.text

    Except requests.RequestException:

       Return None

Def get_url_and_name(url):

    "The passed argument is the main page link, the return value is a list with 2 elements, element 1 is the map package link, and element 2 is the map package name."

    Html=get_html(url)

    Soup=BeautifulSoup(html,'lxml')

    Name=[]

    Url_1=[]

    List2=soup.find_all(class_='t')

    Sign=1

    For item in list2:

        If(sign!=1 and sign!=42):

            Url_temp=item.find('a').get('href')

            Name_temp=item.find(class_='title').find('a').get('title')

            Url_1.append(url_temp)

            Name.append(name_temp)

        Sign=sign+1

    Temp=[url_1,name]

    Return temp

Def get_pic_url(url):

    "The argument passed in is the link to the map package, and the return value is the link to all the images in the map package."

    Address=[]

    Html1=get_html(url)

    Soup=BeautifulSoup(html1,'lxml')

    List4=soup.find(class_='page').find_all('a')

    Temp=1

    While(temp<len(list4)):

        If(temp==1):

            Url_3=url

        Else:

            Url_3=url.replace('.html','_'+str(temp)+'.html')

        Temp=temp+1

        Html2=get_html(url_3)

        Soup1=BeautifulSoup(html2,'lxml')

        List3=soup1.find(class_='content').find_all('img')

        For item in list3:

            Address.append(item.get('src'))

    Return address

    

Def pic_download(url,name,path):

    "url is a list of all image links for a map package, name is the name of the package, and path is the downloaded directory."

    Os.mkdir(path+'./'+name)

    # Because the mkdir function is used, it is necessary to ensure that the folder to be created cannot exist, otherwise an error will be reported.

    Print('The package being downloaded is named '+name')

    Index=1

    For i1 in url:

        Filename = path+'./'+name+'./'+str(index) +'.jpg'

        With open(filename, 'wb') as f:

            Img = requests.get(i1).content

            F.write(img)

        Index += 1

        Time.sleep(2)

    Print(name+'download completed!')

Def main(i):

#i is the number of pages of the homepage of the map (the first few pages)

    Url='https://www.keke234.com/gaoqing/list_5_'+str(i)+'.html'

    Path=r'H:\autoDownLoadPictures\savePicture'

#path is a custom path

    Information=get_url_and_name(url)

    Num=0

    For item in information[0]:

        Address=get_pic_url(item)

        Pic_download(address,information[1][num],path)

        Num=num+1

If __name__ == '__main__':

    For i in range(1,2):

        Main(i)