溫馨提示×
您好，登錄后才能下訂單哦！
點擊 登錄注冊 即表示同意《億速云用戶服務條款》
您好，登錄后才能下訂單哦！
這篇文章將為大家詳細講解有關python如何學習requests爬取網頁圖片，小編覺得挺實用的，因此分享給大家做個參考，希望大家閱讀完這篇文章后可以有所收獲。
??最近想做一個練練的小游戲給家里的小朋友玩兒，但是苦于選取素材，然后在一個巨佬的博客里找了靈感，就借用一下粉絲的頭像試試爬取網頁里的圖片吧！
?
完成總目標：
??爬取粉絲頭像作為素材，完成一個連連看的小游戲
故本文分為兩部分內容：
1、爬取素材部分；
2、利用素材完成連連看小游戲部分(鏈接)
實現目標：
??通過爬蟲實現對粉絲頭像的爬取并順序排列存儲，作為游戲設計的素材，其中爬取的頭像一部分是使用了CSDN的默認頭像，存在重復情況，所以還需要去重以得到完整且不重復的圖像集
一、準備
1、python環境
2、涉及到的python庫需要 pip install 包名 安裝
二、代碼編寫
1.爬取內容
（1）所需要的庫
import requestsimport json
（2）得到請求地址
url = 'https://blog.csdn.net//phoenix/web/v1/fans/list?page=1&pageSize=40&blogUsername=weixin_45386875' #關注我的部分請求地址#url = 'https://blog.csdn.net//phoenix/web/v1/follow/list?page=1&pageSize=40&blogUsername=weixin_45386875' #我關注的部分請求地址
請求地址獲取方法：
右擊所要爬取部分頁面，點擊 審查元素，找到圖中文件
注： 頁面選到“TA的粉絲（13）”部分才能出現，如果點擊Network什么也沒有，則需要刷新頁面就會出現頁面內容了）
（3）帶上請求頭發送請求，做一些簡單偽裝
header = {
'User-Agent' : 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36',
'Cookie' : 'uuid_tt_dd=10_30826311340-1612520858912-361156; Hm_ct_6bcd52f51e9b3dce32bec4a3997715ac=6525*1*10_30826311340-1612520858912-361156!5744*1*weixin_45386875!1788*1*PC_VC; UN=weixin_45386875; p_uid=U010000; ssxmod_itna=Qui=DKiI3hkbG=DXDnD+r8h9eD53ecxPPit5bP1ODlOaYxA5D8D6DQeGTbcW1AoWGATqFYKmEWiH5/gbO4FpjQGcxLbbYx0aDbqGkqnU40rDzuQGuD0KGRDD4GEDCHHDIxGUBuDeKDR8qDg7gQcCM=DbSdDKqDHR+4FbG4oD8PdS0p=C7Gt3AuQ3DmtSije3r424rQ+iPqWzPDA3DK6jiD==; ssxmod_itna2=Qui=DKiI3hkbG=DXDnD+r8h9eD53ecxPPit5bP1D66Ii40vah403pFcXW0D6QALW==0tWLGtzKPUA76xoU10vpqD6AoOqs1R=Db=3olozYp0wVxUS0r/GeZCqzVezFQc8dZon7efYcr=1nhNr6nWKcTqqaDQYcwYSA+hNaqem=WWuDuDQ/+1PGEsN=atvS7WDp07vFuFDherg0AP0KFw0ea6kcTtK2rh/fy=/De0n1FNk+ONYxCXr=QrdTj6gxCuNNWXvp1IDdl2Ckjc=N/cqV6SmHZIZIuOEqml=dHMroMFDvdMVr8afnyQ+sbGPCbt3xdD07tAdRD7uDQ0gT=Bh7OYblbtYQFDDLxD2tGDD===; UserName=weixin_45386875; UserInfo=9863b829527c49a3ba1622396deaa7d9; UserToken=9863b829527c49a3ba1622396deaa7d9; UserNick=ryc875327878; AU=01F; BT=1612846374580; Hm_up_6bcd52f51e9b3dce32bec4a3997715ac=%7B%22uid_%22%3A%7B%22value%22%3A%22weixin_45386875%22%2C%22scope%22%3A1%7D%2C%22islogin%22%3A%7B%22value%22%3A%221%22%2C%22scope%22%3A1%7D%2C%22isonline%22%3A%7B%22value%22%3A%221%22%2C%22scope%22%3A1%7D%2C%22isvip%22%3A%7B%22value%22%3A%220%22%2C%22scope%22%3A1%7D%7D; __gads=ID=94978f740e79c9e5-22c918ed05c600ea:T=1613266189:RT=1613266189:S=ALNI_Mbwb8ad5kdYjogF7yImerVAzKaJuQ; dc_session_id=10_1613272889543.735028; announcement-new=%7B%22isLogin%22%3Atrue%2C%22announcementUrl%22%3A%22https%3A%2F%2Fblog.csdn.net%2Fblogdevteam%2Farticle%2Fdetails%2F112280974%3Futm_source%3Dgonggao_0107%22%2C%22announcementCount%22%3A0%2C%22announcementExpire%22%3A3600000%7D; dc_sid=3784575ebe1e9d08a29b0e3fc3621328; c_first_ref=default; c_first_page=https%3A//www.csdn.net/; c_segment=4; Hm_lvt_6bcd52f51e9b3dce32bec4a3997715ac=1613222907,1613266055,1613268241,1613273899; TY_SESSION_ID=82f0aa61-9b28-49b2-a854-b18414426735; c_pref=; c_ref=https%3A//www.csdn.net/; c_page_id=default; dc_tos=qoi2fq; log_Id_pv=925; Hm_lpvt_6bcd52f51e9b3dce32bec4a3997715ac=1613274327; log_Id_view=905; log_Id_click=658'
}獲取請求頭的方法：
（4）向網頁發送請求
try:
data = requests.get(url,headers = header).text
data_dist = json.loads(data)
except:
print('爬取失敗')
exit ()2.保存所需圖片并去重
定義一些函數備用
#保存文件def save_imag(file_name,img_url): request.urlretrieve(url=img_url,filename='D:\\ryc\python_learning\\10_linkup\\fan_avatar\\'+file_name)
#刪除一個文件夾下的所有所有文件def del_file(path):
ls = os.listdir(path)
for i in ls:
c_path = os.path.join(path, i)
if os.path.isdir(c_path):#如果是文件夾那么遞歸調用一下
del_file(c_path)
else: #如果是一個文件那么直接刪除
os.remove(c_path)
print ('文件已經清空完成')#圖像去重def compare_images(pic1,pic2):
image1 = Image.open(pic1)
image2 = Image.open(pic2)
histogram1 = image1.histogram()
histogram2 = image2.histogram()
differ = math.sqrt(reduce(operator.add, list(map(lambda a,b: (a-b)**2,histogram1, histogram2)))/len(histogram1))
print('differ:',differ)
if differ == 0:
return 'same'
else:
return 'diff'#刪除指定位置的圖像def del_avatar(path):
if os.path.exists(path): # 如果文件存在
os.remove(path)
else:
print('no such file:%s'%(path)) # 則返回文件不存在#先清空一下文件夾
del_file('D:\\ryc\python_learning\\10_linkup\\fan_avatar')
index = 0
# i 是爬取列表的索引號； index 是保存的圖片的索引號
for i in range(0,len(fan_list)):
fan_username = fan_list[i]['nickname']
#print('fans_user%s:'%(i+1),fan_username)
fan_avatar_url = fan_list[i]['userAvatar']
#print('fans_avatar_url%s:'%(i+1),fan_avatar_url)
save_imag('fans_avatar%s.jpg'%(index+1),fan_avatar_url)
#print('----------------save_image--fans_avatar%s.jpg'%(index+1))
#圖片去重
for j in range(0,index):
if index != j :
comp_res = compare_images('./fan_avatar/fans_avatar%s.jpg'%(index+1),'./fan_avatar/fans_avatar%s.jpg'%(j+1))
print('--------compare_images:--------'+'./fan_avatar/fans_avatar%s.jpg'%(index+1) + '------with---' + './fan_avatar/fans_avatar%s.jpg'%(j+1))
print('comp_res:',comp_res)
if comp_res == 'same':
del_avatar('D:\\ryc\python_learning\\10_linkup\\fan_avatar\\fans_avatar%s.jpg'%(index+1))
print('D:\\ryc\python_learning\\10_linkup\\fan_avatar\\fans_avatar%s.jpg'%(index+1))
index = index - 1
break
index = index + 13、調用
if __name__ == "__main__": spider_fanavatar()
三、完整代碼
# 爬取網頁圖片import requestsfrom urllib import requestimport jsonfrom PIL import Imageimport osimport mathimport operatorfrom functools import reduce#保存文件def save_imag(file_name,img_url):
request.urlretrieve(url=img_url,filename='D:\\ryc\python_learning\\10_linkup\\fan_avatar\\'+file_name)#爬取粉絲的頭像def spider_fanavatar():
url = 'https://blog.csdn.net//phoenix/web/v1/fans/list?page=1&pageSize=40&blogUsername=weixin_45386875' #關注我的部分請求地址
#url = 'https://blog.csdn.net//phoenix/web/v1/follow/list?page=1&pageSize=40&blogUsername=weixin_45386875' #我關注的部分請求地址
header = {
'User-Agent' : 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36',
'Cookie' : 'uuid_tt_dd=10_30826311340-1612520858912-361156; Hm_ct_6bcd52f51e9b3dce32bec4a3997715ac=6525*1*10_30826311340-1612520858912-361156!5744*1*weixin_45386875!1788*1*PC_VC; UN=weixin_45386875; p_uid=U010000; ssxmod_itna=Qui=DKiI3hkbG=DXDnD+r8h9eD53ecxPPit5bP1ODlOaYxA5D8D6DQeGTbcW1AoWGATqFYKmEWiH5/gbO4FpjQGcxLbbYx0aDbqGkqnU40rDzuQGuD0KGRDD4GEDCHHDIxGUBuDeKDR8qDg7gQcCM=DbSdDKqDHR+4FbG4oD8PdS0p=C7Gt3AuQ3DmtSije3r424rQ+iPqWzPDA3DK6jiD==; ssxmod_itna2=Qui=DKiI3hkbG=DXDnD+r8h9eD53ecxPPit5bP1D66Ii40vah403pFcXW0D6QALW==0tWLGtzKPUA76xoU10vpqD6AoOqs1R=Db=3olozYp0wVxUS0r/GeZCqzVezFQc8dZon7efYcr=1nhNr6nWKcTqqaDQYcwYSA+hNaqem=WWuDuDQ/+1PGEsN=atvS7WDp07vFuFDherg0AP0KFw0ea6kcTtK2rh/fy=/De0n1FNk+ONYxCXr=QrdTj6gxCuNNWXvp1IDdl2Ckjc=N/cqV6SmHZIZIuOEqml=dHMroMFDvdMVr8afnyQ+sbGPCbt3xdD07tAdRD7uDQ0gT=Bh7OYblbtYQFDDLxD2tGDD===; UserName=weixin_45386875; UserInfo=9863b829527c49a3ba1622396deaa7d9; UserToken=9863b829527c49a3ba1622396deaa7d9; UserNick=ryc875327878; AU=01F; BT=1612846374580; Hm_up_6bcd52f51e9b3dce32bec4a3997715ac=%7B%22uid_%22%3A%7B%22value%22%3A%22weixin_45386875%22%2C%22scope%22%3A1%7D%2C%22islogin%22%3A%7B%22value%22%3A%221%22%2C%22scope%22%3A1%7D%2C%22isonline%22%3A%7B%22value%22%3A%221%22%2C%22scope%22%3A1%7D%2C%22isvip%22%3A%7B%22value%22%3A%220%22%2C%22scope%22%3A1%7D%7D; __gads=ID=94978f740e79c9e5-22c918ed05c600ea:T=1613266189:RT=1613266189:S=ALNI_Mbwb8ad5kdYjogF7yImerVAzKaJuQ; dc_session_id=10_1613272889543.735028; announcement-new=%7B%22isLogin%22%3Atrue%2C%22announcementUrl%22%3A%22https%3A%2F%2Fblog.csdn.net%2Fblogdevteam%2Farticle%2Fdetails%2F112280974%3Futm_source%3Dgonggao_0107%22%2C%22announcementCount%22%3A0%2C%22announcementExpire%22%3A3600000%7D; dc_sid=3784575ebe1e9d08a29b0e3fc3621328; c_first_ref=default; c_first_page=https%3A//www.csdn.net/; c_segment=4; Hm_lvt_6bcd52f51e9b3dce32bec4a3997715ac=1613222907,1613266055,1613268241,1613273899; TY_SESSION_ID=82f0aa61-9b28-49b2-a854-b18414426735; c_pref=; c_ref=https%3A//www.csdn.net/; c_page_id=default; dc_tos=qoi2fq; log_Id_pv=925; Hm_lpvt_6bcd52f51e9b3dce32bec4a3997715ac=1613274327; log_Id_view=905; log_Id_click=658'
}
try:
data = requests.get(url,headers = header).text #得到返回的字符串
data_dist = json.loads(data) #將字符串轉為字典格式
except:
print('爬取失敗')
exit ()
fan_list = data_dist['data']['list'] #提取所需內容
#先清空一下文件夾
del_file('D:\\ryc\python_learning\\10_linkup\\fan_avatar')
index = 0
# i 是爬取列表的索引號； index 是保存的圖片的索引號
for i in range(0,len(fan_list)):
fan_username = fan_list[i]['nickname']
#print('fans_user%s:'%(i+1),fan_username)
fan_avatar_url = fan_list[i]['userAvatar']
#print('fans_avatar_url%s:'%(i+1),fan_avatar_url)
save_imag('fans_avatar%s.jpg'%(index+1),fan_avatar_url)
#print('----------------save_image--fans_avatar%s.jpg'%(index+1))
#圖片去重
for j in range(0,index):
if index != j :
comp_res = compare_images('./fan_avatar/fans_avatar%s.jpg'%(index+1),'./fan_avatar/fans_avatar%s.jpg'%(j+1))
print('--------compare_images:--------'+'./fan_avatar/fans_avatar%s.jpg'%(index+1) + '------with---' + './fan_avatar/fans_avatar%s.jpg'%(j+1))
print('comp_res:',comp_res)
if comp_res == 'same':
del_avatar('D:\\ryc\python_learning\\10_linkup\\fan_avatar\\fans_avatar%s.jpg'%(index+1))
print('D:\\ryc\python_learning\\10_linkup\\fan_avatar\\fans_avatar%s.jpg'%(index+1))
index = index - 1
break
index = index + 1
#圖像去重def compare_images(pic1,pic2):
image1 = Image.open(pic1)
image2 = Image.open(pic2)
histogram1 = image1.histogram()
histogram2 = image2.histogram()
differ = math.sqrt(reduce(operator.add, list(map(lambda a,b: (a-b)**2,histogram1, histogram2)))/len(histogram1))
print('differ:',differ)
if differ == 0:
return 'same'
else:
return 'diff'
#刪除指定位置的圖像def del_avatar(path):
if os.path.exists(path): # 如果文件存在
os.remove(path)
else:
print('no such file:%s'%(path)) # 則返回文件不存在#刪除一個文件夾下的所有所有文件def del_file(path):
ls = os.listdir(path)
for i in ls:
c_path = os.path.join(path, i)
if os.path.isdir(c_path):#如果是文件夾那么遞歸調用一下
del_file(c_path)
else: #如果是一個文件那么直接刪除
os.remove(c_path)
print ('文件已經清空完成')if __name__ == "__main__":
spider_fanavatar()最后
第一部分內容就到這里，第二部分內容將在下一篇文章完成，感興趣的小伙伴可以關注我，然后去看下一片文章哦！
都讀到這里了，各位親愛的讀者留下你們寶貴的贊和評論吧，這將是我繼續前進的堅定動力！！！
關于“python如何學習requests爬取網頁圖片”這篇文章就分享到這里了，希望以上內容可以對大家有一定的幫助，使各位可以學到更多知識，如果覺得文章不錯，請把它分享出去讓更多的人看到。
免責聲明：本站發布的內容（圖片、視頻和文字）以原創、轉載和分享為主，文章觀點不代表本網站立場，如果涉及侵權請聯系站長郵箱：is@yisu.com進行舉報，并提供相關證據，一經查實，將立刻刪除涉嫌侵權內容。
