記錄學(xué)習(xí)Python歷程

簡(jiǎn)單了解語(yǔ)法規(guī)則桩蓉，嘗試?yán)谜齽t采集網(wǎng)站圖片淋纲，結(jié)果還算理想，不過(guò)只寫了手動(dòng)查詢的触机，自動(dòng)采集加倆循環(huán)搞定帚戳，只是語(yǔ)法儲(chǔ)備不足，還是有很多冗余代碼儡首，繼續(xù)學(xué)習(xí)Ｆ巍Ｊ呖琛对供！繼續(xù)擼起袖子加油干，奧利給！６焖琛京景！

import urllib.request
import re
import urllib
#函數(shù)返回值:cod 1為失敗 0為成功

#函數(shù)返回值格式
def return_msg(cod,msg,data):
    res = {}
    res['cod'] = cod
    res['msg'] = msg
    res['data'] = data
    return res

#獲取網(wǎng)頁(yè)源碼
def get_html(url):
    page = urllib.request.urlopen(url)
    html_a = page.read()
    return html_a.decode('utf-8')

#正則提取數(shù)組操作
def re_ac(html,reg):
    re_res = re.compile(reg)
    arr = re_res.findall(html)
    res = return_msg(1,"匹配失敗",'')
    if len(arr) !=0:
        res = return_msg(0, "匹配成功", arr)
    return res

#正則提取數(shù)組操作 允許換行
def re_ac_tall(html,reg):
    re_res = re.compile(reg,re.DOTALL)
    arr = re_res.findall(html)
    res = return_msg(1,"匹配失敗",'')
    if len(arr) != 0:
        res = return_msg(0, "匹配成功", arr)
    return res

#獲取子頁(yè)面地址
def get_son_url(html):
    urllist = re_ac(html,r'<a href="(.*?)" class="img"')
    return urllist

#獲取子頁(yè)面所有圖片
def get_son_img(html):
    imglist =re_ac(html,r'<img class="lazy" src="(.*?)"')
    return imglist

#獲取下一頁(yè)鏈接
def get_nexturl(html):
    urls =re_ac(html,r'<div class="pageNum wp">(.*?)</div>')
    res = urls
    if urls['cod'] == 0:
        nexturl = urls['data']
        if nexturl != '':
            if '下一頁(yè)' in nexturl:
                url = re_ac(nexturl,r '<a href="(.*?)">')
                res = url
                if url['cod'] == 1:
                    res = return_msg(2, "沒(méi)有下一頁(yè)了", '')
            else:
                res = return_msg(2, "沒(méi)有下一頁(yè)了", '')
        else:
            res = return_msg(1, "數(shù)據(jù)匹配失敗", '')
    return res

# 獲取分類
def get_class(html):
    info = re_ac_tall(html,r'<div class="subnav-l z">(.*?)</div>')
    res = info
    if info['cod'] == 0:
        infos = re_ac(info['data'][0], r'href="(.*?)" >(.*?)<')
        if infos['cod'] == 0:
            res = infos
        else:
            res = return_msg(1, "數(shù)據(jù)匹配失敗", '')
    else:
        res = return_msg(1, "數(shù)據(jù)匹配失敗", '')
    return res

host = "https://www."+"wo"+"yao"+"ge"+"xing"+".com"
#讀取圖片
html_b = get_html(host+"/touxiang/")
if html_b != '':
    n_class = get_class(html_b)
    n_class_data = n_class['data']
    if n_class['cod'] == 0:
        while True:
            i = 0
            print("PS:請(qǐng)根據(jù)序號(hào)查詢分類圖片")
            for v in n_class['data']:
                print(str(i) + '---' + str(v[1]))
                i += 1
            index = input("請(qǐng)輸入查詢序號(hào):")
            if index == '-1':
                print("已退出查詢")
                break
            elif int(index) > len(n_class['data']) or int(index) < 0:
                print("請(qǐng)輸入正確的序號(hào)")
            else:
                page = input("請(qǐng)輸入查詢頁(yè)碼:")
                while int(page) <= 0:
                    print("請(qǐng)輸入大于等于1的頁(yè)碼")
                    page = input("請(qǐng)輸入查詢頁(yè)碼:")
                print(host + n_class['data'][int(index)][0] + "index_" + page + ".html")
                class_url = host + n_class['data'][int(index)][0]
                if int(page) > 1:
                    class_url = host + n_class['data'][int(index)][0] + "/index_" + page + ".html"
                html_c = get_html(class_url)
                urllist = get_son_url(html_c)
                if urllist['cod'] == 0:
                    for url in urllist['data']:
                        html = get_html(host + url)
                        imgres = get_son_img(html)
                        if imgres['cod'] == 0:
                            print(imgres['data'])
                        else:
                            break
                            print(imgres)
                else:
                    break
                    print(urllist)
    else:
        print("分類獲取失敗")
else:
    print("數(shù)據(jù)查詢失敗")