資源簡介
利用Python爬蟲批量下載百度圖庫圖片
代碼片段和文件信息
import?urllib.request
import?urllib.parse
import?ssl
import?re
import?pymysql
import?cv2
import?time
import?os
i?=?0
ssl._create_default_https_context?=?ssl._create_unverified_context?
def?open_url(url):
????headers?=?{‘User-Agent‘:‘Mozilla/5.0?(Windows?NT?10.0;?WOW64)?AppleWebKit/537.36?(KHTML?like?Gecko)?Chrome/53.0.2785.104?Safari/537.36?Core/1.53.4843.400?QQBrowser/9.7.13021.400‘}
????req=urllib.request.Request(url=urlheaders=headers)
????‘‘‘req?=?urllib.request.Request(url)
????req.add_header(‘User-Agent‘‘Mozilla/5.0?(Windows?NT?6.1;?WOW64;?rv:23.0)?Gecko/20100101?Firefox/23.0‘)‘‘‘
????page?=?urllib.request.urlopen(req)
????html?=?page.read().decode(‘utf-8‘)
????#print(html)
????return?html
def?get_img(html?file_name?num):
????global?i
????os.mkdir(file_name)
????photo_link?=?r‘“objURL“:“(http://[^“]*.jpg)“‘
????imgs?=?re.findall(photo_link?html)?
????last_link?=?r‘下一頁‘
????last?=?re.findall(last_link?html)
????#print(len(imgs))
????
????try:
????????for?each?in?imgs:
????????????if?i?>?num:
????????????????????print(‘下載結束!‘)
????????????????????return?‘---‘?-1
????????????????????
????????????????????
????????????#print(each
評論
共有 條評論