Python爬取半次元图片[一]

#coser网站图片获取  限制与\u\..


from bs4 import BeautifulSoup
import requests
from urllib import request
import re
import os
from random import randint


def Make_file():
    if os.path.exists("Daily_information.txt") == False:
        f = open("Daily_information.txt", "w")
        f.write("GET\n")
        f.close()


def Check_File():
    if os.path.isdir("Img") == False:
        os.makedirs("Img")


def Url_Write(url):                                                         #url日志系统
    if os.path.exists("Url_text.txt") == False:
        f = open("Url_text.txt","w")
        f.write("\n%s\n"%url)
        f.close()
    else:
        f = open("Url_text.txt","a")
        f.write("%s\n"%url)
        f.close()


def Url_geting(url=‘http://www.baidu.com‘, pat={"Mother": "fucker"}):               #网页缓存返回beautifulSoup对象
    buf = requests.get(url=url,params=pat)               # 读取网站
    try:
        html = BeautifulSoup(buf.text, "lxml")                                          # 使用BeautifulSoup解析
    except Exception as e:                                                               # 防止出错
        f = open("Daily_information.txt","a")
        f.write("%s:%s\n" % (url,e))
    return html

def Title_Get(html):
    Big_Title = html.find_all("h1",attrs = {"class":re.compile("js-post-title")})
    Title = Big_Title[0].text
    return Title

def Title_file_create(Title):                                                               #Title文件夹创建函数
    True_way = "%s"%Title
    os.makedirs(True_way)


def Title_Dispose(Title):                       #Title获取函数
    Title = Title[1:]
    Title = Title.split(":")
    Title = Title[-1]
    Title = Title.replace(" ","")
    return Title


def Img_Link_get(html):                                 #图片链接查找函数(估计只能用在半次元)
    Img_link = []
    Img_Face = html.find_all("img", attrs={"class": re.compile("detail_std")})
    for i in Img_Face:
        Img_link.append(i["src"])
    return Img_link

# 给出登陆用户,链接，获得html，解析html得到Img中href属性,获取Title处理后给做文件名

def Get_information(url = "https://bcy.net/coser/detail/13612/338282",pat = {"Test": "@1"}):
    html = Url_geting(url, pat=pat)
    The_link = Img_Link_get(html=html)
    Title = Title_Get(html)
    Title = Title_Dispose(Title)
    attrs = [url,html,The_link,Title]
    return attrs

def Get_Download(Img_links,path):                           #以后记得传参检查参数，此次bug为未处理传出参数中Title的空格
    if os.path.exists(path) == False:
        os.makedirs(path)
    step = 0
    for i in Img_links:
        step += 1
        request.urlretrieve(i,"%s\\%d.jpg"%(path,step))


pat = [{"门前大桥下":"游过一只鸭"},{"我爱北京天安门":"天安门上太阳升"},{"爱像":"一阵风"},{"吹完他就走":"~~"},{"辣妹儿":"法克儿"}]



if __name__ == "__main__":
    Check_File()
    Make_file()
    print("只可使用半次元coser页图片链接,按q再按enter退出")
    print("请输入链接：")
    while True:
        url = input()

        print("正在下载中....")
        weigth = len(pat)
        pat = pat[randint(0, weigth-1)]
        attrs = Get_information(url, pat)
        path = "Img\\%s" % attrs[3]
            #print(path + ‘1‘
        Get_Download(attrs[2], path=path)
        Url_Write(url=attrs[0])
        print("下载完毕...继续输入链接下载...按q + enter 退出")