348 字
2 分鐘
selenium擷取整頁頁面並截圖元素

介紹#

如果你想擷取網頁中謀個區塊儲存成圖片,可以使用這種方法。

擷取網頁整個頁面#

import selenium.webdriver.chrome.webdriver
import time, os
from PIL import Image
def chrome_take_full_page_screenshot(browser, file):
browser.maximize_window()
time.sleep(0.2)
total_width = browser.execute_script("return document.body.offsetWidth")
total_height = browser.execute_script("return document.body.parentNode.scrollHeight")
viewport_width = browser.execute_script("return document.body.clientWidth")
viewport_height = browser.execute_script("return window.innerHeight")
rectangles = []
i = 0
while i < total_height:
ii = 0
top_height = i + viewport_height
if top_height > total_height:
top_height = total_height
while ii < total_width:
top_width = ii + viewport_width
if top_width > total_width:
top_width = total_width
rectangles.append((ii,i,top_width,top_height))
ii = ii + viewport_width
i = i + viewport_height
stitched_image = Image.new('RGB', (total_width, total_height))
previous = None
part = 0
cache_id = 1
for rectangle in rectangles:
if not previous is None:
browser.execute_script("window.scrollTo({0}, {1})".format(rectangle[0], rectangle[1]))
time.sleep(0.2)
file_name = "scroll_{0}_part_{1}.png".format(cache_id, part)
browser.get_screenshot_as_file(file_name)
screenshot = Image.open(file_name)
if rectangle[1] + viewport_height > total_height:
offset = (rectangle[0], total_height - viewport_height)
else:
offset = (rectangle[0], rectangle[1])
stitched_image.paste(screenshot, offset)
del screenshot
os.remove(file_name)
part = part + 1
previous = rectangle
stitched_image.save(file)
chrome_driver = 'C:/anaconda/chromedriver.exe' #驅動路徑
browser = selenium.webdriver.chrome.webdriver.WebDriver(chrome_driver)
browser.get("https://law.moj.gov.tw/LawClass/LawAll.aspx?pcode=A0000001") #擷取網址
chrome_take_full_page_screenshot(browser, 'img.png') #圖片儲存路徑

擷取元素為圖片#

from selenium import webdriver
from time import sleep
from selenium.webdriver.common.by import By
from selenium.webdriver.common.action_chains import ActionChains
from PIL import Image
import PIL
PIL.Image.MAX_IMAGE_PIXELS = 933120000 #如果圖片pixels很大 設定高一點
url="https://law.moj.gov.tw/LawClass/LawAll.aspx?pcode=A0000001"
driver=webdriver.Chrome("C:/anaconda/chromedriver.exe") #驅動 路徑請設定自己的檔案路徑
driver.get(url)
driver.maximize_window()
sleep(0.3)
content = driver.find_element(By.XPATH, '//*[@id="pnLawFla"]/div/div[165]') #元素位置 #例如:憲法第146條
driver.execute_script("arguments[0].scrollIntoView();", content) #滾動到元素
sleep(0.3)
#取得元素尺寸大小
left=content.location['x']
top=content.location['y']
right=content.location['x'] + content.size['width']
bottom=content.location['y'] + content.size['height']
img=Image.open("img.png") #開啟整頁圖片
img2=img.crop((left,top,right,bottom)) #切圖
img2.save('crop.png') #切圖儲存
# print(left)
# print(top)
# print(right)
# print(bottom)
driver.close()

https://github.com/kobojp/PythonExercise/blob/master/selenium%E6%93%B7%E5%8F%96%E6%95%B4%E9%A0%81%E9%A0%81%E9%9D%A2%E4%B8%A6%E6%88%AA%E5%9C%96%E6%8C%87%E5%AE%9A%E7%9A%84%E5%85%83%E7%B4%A0.ipynb(在新分頁開啟)

selenium擷取整頁頁面並截圖元素
https://aishuafei.com/posts/selenium擷取整頁頁面並截圖元素/
作者
愛耍廢
發佈於
2020-02-16
許可協議
CC BY-NC-SA 4.0