Headless Chrome to give a specific name to a file when downloaded/converted to pdf

user_11634498 0
Viewed 281

I am using headless chrome to convert the webpage to pdf . So I am able to do it but I want to give specific name to the files downloaded (converted to pdf) as at a time I am converting 100+ pdf files using the url.Below is my code. I have tried shutil but the earlier files are deleted and only the latest file remains which I unable to open it.

import os
import time
import json
from selenium import webdriver

try:
    import urlparse
    from urllib import urlencode
except: # For Python 3
    import urllib.parse as urlparse
    from urllib.parse import urlencode

if os.path.exists(".DS_Store"):
    os.remove(".DS_Store")


appState = {
    "recentDestinations": [
        {
            "id": "Save as PDF",
            "origin": "local"
        }
    ],
    "selectedDestinationId": "Save as PDF",
    "version": 2
}

profile = {'printing.print_preview_sticky_settings.appState': json.dumps(appState)}

download_path = r'/Users/expether/Desktop/Diagence/Task 1' # Path where browser save files
new_path = r'/Users/expether/Desktop/Diagence/Task 1/mkpdf' # Path where to move file


photoid = 3
seaid_destination = 2    

searchs = ["merge_recog","shape_recog","pattern_recog"] 


for search in searchs:
    
    url = "http://0.0.0.0:8080/" + search + "?"
    params = {'photoid':photoid,'seaid_destination':seaid_destination}
    
    file_name = search + str(photoid) + "_" + str(seaid_destination) + ".pdf"
    
    url_parse = urlparse.urlparse(url)
    query = url_parse.query            #retrieve query item
    url_dict = dict(urlparse.parse_qsl(query))     #convert the list to dict
    url_dict.update(params)                  #add params to dict
    url_new_query = urlencode(url_dict)            #convert it in "percent-encoded"
    url_parse = url_parse._replace(query=url_new_query)   #replace old query with new query
    new_url = urlparse.urlunparse(url_parse)        #construct new url
    print(new_url)
    
    chrome_options = webdriver.ChromeOptions()
    chrome_options.binary_location = '/Applications/Google Chrome Canary.app/Contents/MacOS/Google Chrome Canary'
    chrome_options.add_experimental_option('prefs', profile)
    chrome_options.add_argument('--kiosk-printing')
    CHROMEDRIVER_PATH = '/Users/expether/Downloads/chromedriver'
    driver = webdriver.Chrome(options=chrome_options, executable_path=CHROMEDRIVER_PATH)
    
    driver.get(new_url)
    
    import shutil
    filename = max([download_path + "/" + f for f in os.listdir(download_path)],key=os.path.getctime)
    shutil.move(filename,os.path.join(download_path,file_name))
    # driver.execute_script('window.print();')
    driver.quit()
selenium-webdriver selenium pdf download python
1 Answers

working code :

from selenium import webdriver
import json
import os
import shutil
import time

try:
    import urlparse
    from urllib import urlencode
except: # For Python 3
    import urllib.parse as urlparse
    from urllib.parse import urlencode

if os.path.exists(".DS_Store"):
    os.remove(".DS_Store")


downloadPath = '/Users/expether/Desktop/Diagence/Task 1'

#for seaid = 4 -> photoid = 1~8
#for seaid = 2 -> photoid = 1~77
photoid = 3
seaid_destination = 2    

searchs = ["merge_recog","shape_recog","pattern_recog"] 

chrome_options = webdriver.ChromeOptions()
settings = {
        "recentDestinations": [{
            "id": "Save as PDF",
            "origin": "local",
            "account": "",
        }],
        "selectedDestinationId": "Save as PDF",
        "version": 2
    }

prefs = {'printing.print_preview_sticky_settings.appState':json.dumps(settings),
           'savefile.default_directory':downloadPath}

chrome_options.binary_location = '/Applications/Google Chrome Canary.app/Contents/MacOS/Google Chrome Canary'
chrome_options.add_experimental_option('prefs', prefs)
chrome_options.add_argument('--kiosk-printing')
CHROMEDRIVER_PATH = '/Users/expether/Downloads/chromedriver'
driver = webdriver.Chrome(options=chrome_options, executable_path=CHROMEDRIVER_PATH)

for search in searchs:
    
    url = "http://0.0.0.0:8080/" + search + "?"
    params = {'photoid':photoid,'seaid_destination':seaid_destination}
    

    url_parse = urlparse.urlparse(url)
    query = url_parse.query            #retrieve query item
    url_dict = dict(urlparse.parse_qsl(query))     #convert the list to dict
    url_dict.update(params)                  #add params to dict
    url_new_query = urlencode(url_dict)            #convert it in "percent-encoded"
    url_parse = url_parse._replace(query=url_new_query)   #replace old query with new query
    new_url = urlparse.urlunparse(url_parse)        #construct new url
    print(new_url) 
    driver.get(new_url)
    driver.execute_script('window.print();')
    
    
    newfilename = search + str(photoid) + "_" + str(seaid_destination) + ".pdf"
    dirpath = '/Users/expether/Desktop/Diagence/Task 1/mkpdf'
    
    # filename = max([downloadPath + '/' + f for f in os.listdir(downloadPath)], key=os.path.getctime)
    # shutil.move(os.path.join(dirpath,filename),newfilename)   
    
    filename = max([downloadPath + "/" + f for f in os.listdir(downloadPath)],key=os.path.getctime)
    shutil.move(filename,os.path.join(dirpath,newfilename))
    
driver.quit()
user_116344980
Related