如何使用 python 将 base64 字符串转换并下载为来自 whatsapp 的图像？
How to convert and download base64 string to images from whatsapp using python?
我正在创建 whatsapp scraper 供我个人使用。我正在尝试从 html 代码下方下载图片：
<div class="_2n28r" style="background-image: url("data:image/jpeg;base64,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");">
但是当我清理 html 并获取 base 64 字符串并将其转换为图像时，我每次都得到损坏的图像
但是当我打印 base 64 字符串并将其粘贴到在线转换网站时，网站会完美地转换它
xx = driver.find_elements_by_class_name("_1iHeu")
d = 0
for m in xx:
getList = m.find_element_by_class_name("_2kLly").find_element_by_class_name("_2n28r").get_attribute("style").split('url("')[1]
d+=1
if len(getList)<10:
continue
var = getList[0:len(getList)-3]
result = base64.b64decode(str(var))
content = result
f1 = open("d"+'_'+str("d")+str(d)+'.png', 'wb')
f1.write( content )
f1.close()
这是我的代码片段。
为了方便起见，我也粘贴了完整的代码：
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.common.action_chains import ActionChains
import time, base64, os, json, glob,io
import csv, requests, urllib, urllib.parse
import urllib.request as request
from PIL import Image
LAST_MESSAGES = 4
WAIT_FOR_CHAT_TO_LOAD = 5 # in secs
message_dic = {}
reject_list = []
driver = webdriver.Chrome("./chromedriver")
wait = WebDriverWait(driver, 10)
path = os.path.dirname(os.path.realpath(__file__))+os.sep
print(path)
total_chats = 0
driver.get("https://web.whatsapp.com/")
time.sleep(20)
def saveImage(name, img_cnt, ele, folder):
global reject_list
try:
news = ele
dm = news.get_attribute("src")
dm = urllib.parse.unquote(dm)
nm = img_cnt
txt = dm#resp.content
if txt.find('blob')!=-1:
result = driver.execute_async_script("""
var uri = arguments[0];
var callback = arguments[1];
var toBase64 = function(buffer){for(var r,n=new Uint8Array(buffer),t=n.length,a=new Uint8Array(4*Math.ceil(t/3)),i=new Uint8Array(64),o=0,c=0;64>c;++c)i[c]="ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/".charCodeAt(c);for(c=0;t-t%3>c;c+=3,o+=4)r=n[c]<<16|n[c+1]<<8|n[c+2],a[o]=i[r>>18],a[o+1]=i[r>>12&63],a[o+2]=i[r>>6&63],a[o+3]=i[63&r];return t%3===1?(r=n[t-1],a[o]=i[r>>2],a[o+1]=i[r<<4&63],a[o+2]=61,a[o+3]=61):t%3===2&&(r=(n[t-2]<<8)+n[t-1],a[o]=i[r>>10],a[o+1]=i[r>>4&63],a[o+2]=i[r<<2&63],a[o+3]=61),new TextDecoder("ascii").decode(a)};
var xhr = new XMLHttpRequest();
xhr.responseType = 'arraybuffer';
xhr.onload = function(){ callback(toBase64(xhr.response)) };
xhr.onerror = function(){ callback(xhr.status) };
xhr.open('GET', uri);
xhr.send();
""", dm)
if type(result) == int :
raise Exception("Request failed with status %s" % result)
result = base64.b64decode(result)
content = result
f1 = open(folder+os.sep+name+'_'+str(nm)+'.png', 'wb')
f1.write( content )
f1.close()
pass
elif txt.find('e=')!=-1:
dm = urllib.parse.unquote(dm)
ind = dm.find('e=')
dm = dm[ind+2:]
resp = requests.get(dm, headers={'User-Agent':'Mozilla Firefox'})
f1 = open(folder+os.sep+name+'_'+str(nm)+'.png', 'wb')
f1.write( resp.content )
f1.close()
except:
reject_list.append( [name] )
print("Unable to load data for images of profile ",name)
def getNewImages(ele):
ele.click()
time.sleep(5)
script = "document.getElementsByClassName('_2y8MV')"
get_data = driver.execute_script(
"""
var abc = document.getElementsByClassName('_2y8MV')
for (var i = 0;i<abc.length;i++){
let ds = abc[i].innerText
if (ds.indexOf("Docs")==17){
abc[i].click()
}
}""")
# var mxn = document.getElementsByClassName("_1iHeu")
# for (var i = 0;i<mxn.length;i++){
# getdata = mxn[i]
# findData = getdata.firstChild.firstChild.getAttribute("style").split('url("')[1]
# if (findData==undefined){
# continue}
# var xx = findData.slice(findData.length,findData.length-2)
# console.log(findData)
# const linkSource = xx;
# const downloadLink = document.createElement("a");
# downloadLink.href = linkSource;
# downloadLink.download = "abc.png";
# downloadLink.click();
# }
# """)
# print(get_data)
time.sleep(5)
xx = driver.find_elements_by_class_name("_1iHeu")
d = 0
for m in xx:
getList = m.find_element_by_class_name("_2kLly").find_element_by_class_name("_2n28r").get_attribute("style").split('url("')[1]
d+=1
if len(getList)<10:
continue
var = getList[0:len(getList)-3]
result = base64.b64decode(str(var))
content = result
f1 = open("d"+'_'+str("d")+str(d)+'.png', 'wb')
f1.write( content )
f1.close()
# Image = driver.find_elements_by_class_name("_275OX")
# print(len(Image))
def chats():
name1 =driver.find_element_by_xpath("//div[@class='DP7CM']/span")
name = driver.find_element_by_xpath("//div[@class='DP7CM']/span").text # profile name
print("Checking chat of ",name)
while name.find('/')!=-1:
name = name.replace('/', ' ')
folder = name[:]
while folder.find(' ')!=-1 and folder.find('+')<2 and folder.find('+')!=-1:
folder = folder.replace(' ','')
folder = path+folder
if not os.path.exists(folder):
os.mkdir( folder )
script = "document.getElementById('pane-side').scrollTo(5000,1)"
# script = "document.getElementsByClassName('_2nmDZ')[0].scrollTo(5000, 1)"
cnt =0
ln = len( driver.find_elements_by_xpath("//div[@class='_3dtfX']") )
# print(ln)
while ln<3:
driver.execute_script( script )
time.sleep(2)
cnt += 1
ln = len( driver.find_elements_by_xpath("//div[@class='_3dtfX']") )
if cnt>20 or ln>3:
break
# main = driver.find_element_by_id('main')
# image = main.find_element_by_xpath("//img[@class='_39rvu _20GbR']")
# print(image.get_attribute("src"))
# message_dic[name].append(image.get_attribute('src'))
# data = driver.find_elements_by_xpath('//div[@class="_2kLly"]')[0]
# print(data)
# get_images = data.find_elements_by_tag_name("img")
# print(get_images)
# nm = len( glob.glob(folder+os.sep+"*.png") )
# for news in get_images:
# dm = news.get_attribute("src")
# if image.get_attribute('src')==dm or dm.find('data')!=-1:
# continue
# nm += 1
saveImage(name, str(nm), news, folder)
getNewImages(name1)
def scrape_Image():
recentList = driver.find_elements_by_class_name("_210SC")
recentList.sort(key=lambda x: int(x.get_attribute('style').split("translateY(")[1].split('px')[0]), reverse=False)
start = 0
# script = "document.getElementById('pane-side').scrollTo(0,50000)"
# driver.execute_script(script);
for l in recentList[start:]:
try:
l.click()
time.sleep(WAIT_FOR_CHAT_TO_LOAD)
chats()
next_focus = l
# total_chats += 1
except Exception as e:
print( e )
print("Error in checking next chat")
scrape_Image()
如评论所述，您忘记删除代码中的“data:image/jpeg;base64,”。
如果您的 python 版本大于 3.4，您可以这样做：
from urllib.request import urlopen
getList = m.find_element_by_class_name("_2kLly").find_element_by_class_name("_2n28r").get_attribute("style").split('"')[1]
# now getList is "data:image/jpeg;base64,/9j/4AAQ..."
with urlopen(getList) as response, open('image.png', 'wb') as f:
f.write(response.read())
见
我正在创建 whatsapp scraper 供我个人使用。我正在尝试从 html 代码下方下载图片：
<div class="_2n28r" style="background-image: url("data:image/jpeg;base64,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");">
但是当我清理 html 并获取 base 64 字符串并将其转换为图像时，我每次都得到损坏的图像 但是当我打印 base 64 字符串并将其粘贴到在线转换网站时，网站会完美地转换它
xx = driver.find_elements_by_class_name("_1iHeu")
d = 0
for m in xx:
getList = m.find_element_by_class_name("_2kLly").find_element_by_class_name("_2n28r").get_attribute("style").split('url("')[1]
d+=1
if len(getList)<10:
continue
var = getList[0:len(getList)-3]
result = base64.b64decode(str(var))
content = result
f1 = open("d"+'_'+str("d")+str(d)+'.png', 'wb')
f1.write( content )
f1.close()
这是我的代码片段。
为了方便起见，我也粘贴了完整的代码：
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.common.action_chains import ActionChains
import time, base64, os, json, glob,io
import csv, requests, urllib, urllib.parse
import urllib.request as request
from PIL import Image
LAST_MESSAGES = 4
WAIT_FOR_CHAT_TO_LOAD = 5 # in secs
message_dic = {}
reject_list = []
driver = webdriver.Chrome("./chromedriver")
wait = WebDriverWait(driver, 10)
path = os.path.dirname(os.path.realpath(__file__))+os.sep
print(path)
total_chats = 0
driver.get("https://web.whatsapp.com/")
time.sleep(20)
def saveImage(name, img_cnt, ele, folder):
global reject_list
try:
news = ele
dm = news.get_attribute("src")
dm = urllib.parse.unquote(dm)
nm = img_cnt
txt = dm#resp.content
if txt.find('blob')!=-1:
result = driver.execute_async_script("""
var uri = arguments[0];
var callback = arguments[1];
var toBase64 = function(buffer){for(var r,n=new Uint8Array(buffer),t=n.length,a=new Uint8Array(4*Math.ceil(t/3)),i=new Uint8Array(64),o=0,c=0;64>c;++c)i[c]="ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/".charCodeAt(c);for(c=0;t-t%3>c;c+=3,o+=4)r=n[c]<<16|n[c+1]<<8|n[c+2],a[o]=i[r>>18],a[o+1]=i[r>>12&63],a[o+2]=i[r>>6&63],a[o+3]=i[63&r];return t%3===1?(r=n[t-1],a[o]=i[r>>2],a[o+1]=i[r<<4&63],a[o+2]=61,a[o+3]=61):t%3===2&&(r=(n[t-2]<<8)+n[t-1],a[o]=i[r>>10],a[o+1]=i[r>>4&63],a[o+2]=i[r<<2&63],a[o+3]=61),new TextDecoder("ascii").decode(a)};
var xhr = new XMLHttpRequest();
xhr.responseType = 'arraybuffer';
xhr.onload = function(){ callback(toBase64(xhr.response)) };
xhr.onerror = function(){ callback(xhr.status) };
xhr.open('GET', uri);
xhr.send();
""", dm)
if type(result) == int :
raise Exception("Request failed with status %s" % result)
result = base64.b64decode(result)
content = result
f1 = open(folder+os.sep+name+'_'+str(nm)+'.png', 'wb')
f1.write( content )
f1.close()
pass
elif txt.find('e=')!=-1:
dm = urllib.parse.unquote(dm)
ind = dm.find('e=')
dm = dm[ind+2:]
resp = requests.get(dm, headers={'User-Agent':'Mozilla Firefox'})
f1 = open(folder+os.sep+name+'_'+str(nm)+'.png', 'wb')
f1.write( resp.content )
f1.close()
except:
reject_list.append( [name] )
print("Unable to load data for images of profile ",name)
def getNewImages(ele):
ele.click()
time.sleep(5)
script = "document.getElementsByClassName('_2y8MV')"
get_data = driver.execute_script(
"""
var abc = document.getElementsByClassName('_2y8MV')
for (var i = 0;i<abc.length;i++){
let ds = abc[i].innerText
if (ds.indexOf("Docs")==17){
abc[i].click()
}
}""")
# var mxn = document.getElementsByClassName("_1iHeu")
# for (var i = 0;i<mxn.length;i++){
# getdata = mxn[i]
# findData = getdata.firstChild.firstChild.getAttribute("style").split('url("')[1]
# if (findData==undefined){
# continue}
# var xx = findData.slice(findData.length,findData.length-2)
# console.log(findData)
# const linkSource = xx;
# const downloadLink = document.createElement("a");
# downloadLink.href = linkSource;
# downloadLink.download = "abc.png";
# downloadLink.click();
# }
# """)
# print(get_data)
time.sleep(5)
xx = driver.find_elements_by_class_name("_1iHeu")
d = 0
for m in xx:
getList = m.find_element_by_class_name("_2kLly").find_element_by_class_name("_2n28r").get_attribute("style").split('url("')[1]
d+=1
if len(getList)<10:
continue
var = getList[0:len(getList)-3]
result = base64.b64decode(str(var))
content = result
f1 = open("d"+'_'+str("d")+str(d)+'.png', 'wb')
f1.write( content )
f1.close()
# Image = driver.find_elements_by_class_name("_275OX")
# print(len(Image))
def chats():
name1 =driver.find_element_by_xpath("//div[@class='DP7CM']/span")
name = driver.find_element_by_xpath("//div[@class='DP7CM']/span").text # profile name
print("Checking chat of ",name)
while name.find('/')!=-1:
name = name.replace('/', ' ')
folder = name[:]
while folder.find(' ')!=-1 and folder.find('+')<2 and folder.find('+')!=-1:
folder = folder.replace(' ','')
folder = path+folder
if not os.path.exists(folder):
os.mkdir( folder )
script = "document.getElementById('pane-side').scrollTo(5000,1)"
# script = "document.getElementsByClassName('_2nmDZ')[0].scrollTo(5000, 1)"
cnt =0
ln = len( driver.find_elements_by_xpath("//div[@class='_3dtfX']") )
# print(ln)
while ln<3:
driver.execute_script( script )
time.sleep(2)
cnt += 1
ln = len( driver.find_elements_by_xpath("//div[@class='_3dtfX']") )
if cnt>20 or ln>3:
break
# main = driver.find_element_by_id('main')
# image = main.find_element_by_xpath("//img[@class='_39rvu _20GbR']")
# print(image.get_attribute("src"))
# message_dic[name].append(image.get_attribute('src'))
# data = driver.find_elements_by_xpath('//div[@class="_2kLly"]')[0]
# print(data)
# get_images = data.find_elements_by_tag_name("img")
# print(get_images)
# nm = len( glob.glob(folder+os.sep+"*.png") )
# for news in get_images:
# dm = news.get_attribute("src")
# if image.get_attribute('src')==dm or dm.find('data')!=-1:
# continue
# nm += 1
saveImage(name, str(nm), news, folder)
getNewImages(name1)
def scrape_Image():
recentList = driver.find_elements_by_class_name("_210SC")
recentList.sort(key=lambda x: int(x.get_attribute('style').split("translateY(")[1].split('px')[0]), reverse=False)
start = 0
# script = "document.getElementById('pane-side').scrollTo(0,50000)"
# driver.execute_script(script);
for l in recentList[start:]:
try:
l.click()
time.sleep(WAIT_FOR_CHAT_TO_LOAD)
chats()
next_focus = l
# total_chats += 1
except Exception as e:
print( e )
print("Error in checking next chat")
scrape_Image()
如评论所述，您忘记删除代码中的“data:image/jpeg;base64,”。
如果您的 python 版本大于 3.4，您可以这样做：
from urllib.request import urlopen
getList = m.find_element_by_class_name("_2kLly").find_element_by_class_name("_2n28r").get_attribute("style").split('"')[1]
# now getList is "data:image/jpeg;base64,/9j/4AAQ..."
with urlopen(getList) as response, open('image.png', 'wb') as f:
f.write(response.read())
见