技術標籤：python的學習之旅python百度爬蟲

python爬蟲實戰之爬取任意百度圖片（升級版）

import re
import requests
from urllib import error
from bs4 import BeautifulSoup
import os
 
num = 0
numPicture = 0
file = ''
List = []
 
 
def Find(url, A):
    global List
    print('正在檢測圖片總數，請稍等.....')
    t = 0
    i = 1
    s = 0
    while t <
 
 1000:
        Url = url + str(t)
        try:
            Result = A.get(Url, timeout=7, allow_redirects=False)
        except BaseException:
            t = t + 60
            continue
        else:
            result = Result.text
            pic_url = re.findall('"objURL":"(.*?)",'
 
, result, re.S)  # 先利用正則表示式找到圖片url
            s += len(pic_url)
            if len(pic_url) == 0:
                break
            else:
                List.append(pic_url)
                t = t + 60
    return s
 
 
 
def recommend(url):
    Re = []
    try:
        html = requests.get(url, allow_redirects=
 
False)
    except error.HTTPError as e:
        return
    else:
        html.encoding = 'utf-8'
        bsObj = BeautifulSoup(html.text, 'html.parser')
        div = bsObj.find('div', id='topRS')
        if div is not None:
            listA = div.findAll('a')
            for i in listA:
                if i is not None:
                    Re.append(i.get_text())
        return Re
 
def dowmloadPicture(html, keyword):
    global num
    # t =0
    pic_url = re.findall('"objURL":"(.*?)",', html, re.S)  # 先利用正則表示式找到圖片url
    print('找到關鍵詞:' + keyword + '的圖片，即將開始下載圖片...')
    for each in pic_url:
        print('正在下載第' + str(num + 1) + '張圖片，圖片地址:' + str(each))
        try:
            if each is not None:
                pic = requests.get(each, timeout=7)
            else:
                continue
        except BaseException:
            print('錯誤，當前圖片無法下載')
            continue
        else:
            string = file + r'\\' + keyword + '_' + str(num) + '.jpg'
            fp = open(string, 'wb')
            fp.write(pic.content)
            fp.close()
            num += 1
        if num >= numPicture:
            return
 
 
if __name__ == '__main__':  # 主函式入口
    
    
    headers = {
        'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
        'Connection': 'keep-alive',
        'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:60.0) Gecko/20100101 Firefox/60.0',
        'Upgrade-Insecure-Requests': '1'
        }
 
    A = requests.Session()
    A.headers = headers
    
    
    ###############################
    
    
    tm = int(input('請輸入每類圖片的下載數量 '))
    numPicture = tm
    line_list = []
    print("請輸入你要輸入幾個關鍵詞：")
    i=int(input(""))
    for j in range(i):
        t=input("")
        line_list.append(t)

 
    for word in line_list:
        url = 'https://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word=' + word + '&pn='
        tot = Find(url,A)
        Recommend = recommend(url)  # 記錄相關推薦
        print('經過檢測%s類圖片共有%d張' % (word, tot))
        file = word + '檔案'
        y = os.path.exists(file)
        if y == 1:
            print('該檔案已存在，請重新輸入')
            file = word+'資料夾2'
            os.mkdir(file)
        else:
            os.mkdir(file)
        t = 0
        tmp = url
        while t < numPicture:
            try:
                url = tmp + str(t)
                #result = requests.get(url, timeout=10)
                # 這裡搞了下
                result = A.get(url, timeout=10, allow_redirects=False)
                print(url)
            except error.HTTPError as e:
                print('網路錯誤，請調整網路後重試')
                t = t + 60
            else:
                dowmloadPicture(result.text, word)
                t = t + 60
        numPicture = numPicture + tm
        
    print('當前搜尋結束，感謝使用')

lsp了