python selenium下载失败_Python：无法在网页中使用selenium下载

小编典典

我认为您的主要问题可能是错误的模仿类型，但是，您的脚本有系统性问题的日志，这会使它充其量是不可靠的。此重写使用显式等待，这完全消除了对use的需要time.sleep()，从而使其能够尽可能快地运行，同时还消除了由于网络拥塞而导致的错误。

您需要执行以下操作以确保已安装所有模块：

pip install requests explicit selenium retry pyvirtualdisplay

The script:

#!/usr/bin/python

from __future__ import print_function # Makes your code portable

import os

import glob

import zipfile

from contextlib import contextmanager

import requests

from retry import retry

from explicit import waiter, XPATH, ID

from selenium import webdriver

from pyvirtualdisplay import Display

from selenium.webdriver.common.keys import Keys

from selenium.webdriver.support.wait import WebDriverWait

DOWNLOAD_DIR = "/tmp/shKLSE/"

def build_profile():

profile = webdriver.FirefoxProfile()

profile.set_preference('browser.download.folderList', 2)

profile.set_preference('browser.download.manager.showWhenStarting', False)

profile.set_preference('browser.download.dir', DOWNLOAD_DIR)

# I think your `/zip` mime type was incorrect. This works for me

profile.set_preference('browser.helperApps.neverAsk.saveToDisk',

'application/vnd.ms-excel,application/zip')

return profile

# Retry is an elegant way to retry the browser creation

# Though you should narrow the scope to whatever the actual exception is you are

# retrying on

@retry(Exception, tries=5, delay=3)

@contextmanager # This turns get_browser into a context manager

def get_browser():

# Use a context manager with Display, so it will be closed even if an

# exception is thrown

profile = build_profile()

with Display(visible=0, size=(800, 600)):

browser = webdriver.Firefox(profile)

print("firefox")

try:

yield browser

finally:

# Let a try/finally block manage closing the browser, even if an

# exception is called

browser.quit()

def main():

print("hello from python 2")

with get_browser() as browser:

browser.get("https://www.shareinvestor.com/my")

# Click the login button

# waiter is a helper function that makes it easy to use explicit waits

# with it you dont need to use time.sleep() calls at all

login_xpath = '//*/div[@class="sic_logIn-bg"]/a'

waiter.find_element(browser, login_xpath, XPATH).click()

print(browser.current_url)

# Log in

username = "bkcollection"

username_id = "sic_login_header_username"

password = "123456"

password_id = "sic_login_header_password"

waiter.find_write(browser, username_id, username, by=ID)

waiter.find_write(browser, password_id, password, by=ID, send_enter=True)

# Wait for login process to finish by locating an element only found

# after logging in, like the Logged In Nav

nav_id = 'sic_loggedInNav'

waiter.find_element(browser, nav_id, ID)

print("log in done")

# Load the target page

target_url = ("https://www.shareinvestor.com/prices/price_download.html#/?"

"type=price_download_all_stocks_bursa")

browser.get(target_url)

print(browser.current_url)

# CLick download button

all_data_xpath = ("//*[@href='/prices/price_download_zip_file.zip?"

"type=history_all&market=bursa']")

waiter.find_element(browser, all_data_xpath, XPATH).click()

# This is a bit challenging: You need to wait until the download is complete

# This file is 220 MB, it takes a while to complete. This method waits until

# there is at least one file in the dir, then waits until there are no

# filenames that end in `.part`

# Note that is is problematic if there is already a file in the target dir. I

# suggest looking into using the tempdir module to create a unique, temporary

# directory for downloading every time you run your script

print("Waiting for download to complete")

at_least_1 = lambda x: len(x("{0}/*.zip*".format(DOWNLOAD_DIR))) > 0

WebDriverWait(glob.glob, 300).until(at_least_1)

no_parts = lambda x: len(x("{0}/*.part".format(DOWNLOAD_DIR))) == 0

WebDriverWait(glob.glob, 300).until(no_parts)

print("Download Done")

# Now do whatever it is you need to do with the zip file

# zip_ref = zipfile.ZipFile(DOWNLOAD_DIR, 'r')

# zip_ref.extractall(DOWNLOAD_DIR)

# zip_ref.close()

# os.remove(zip_ref)

print("Done!")

if __name__ == "__main__":

main()

完全公开：我维护显式模块。它旨在使显式等待变得更容易，因为在这种情况下，网站会根据用户交互缓慢加载动态内容。您可以用直接显式等待替换上面的所有waiter.XXX调用。

2020-06-26