"""
really used in fetching url from google images
"""
import re
from selenium import webdriver
import time
import os
import sys
import re
from bs4 import BeautifulSoup
import random
from selenium.webdriver.chrome.options import Options
down_loading_urls = range(1,50)
if __name__ == "__main__":
baidu_path = 'color_co'
temp_path = baidu_path + "/" + "temp_color2.txt"
path = baidu_path + "/" + "color2.txt"
# os.environ["PATH"] += os.pathsep + 'D:\google-art-downloader-master'
if not os.path.exists(baidu_path):
os.makedirs(baidu_path)
# option = webdriver.ChromeOptions()
# option.add_argument('--headless')
# option.add_argument('--disable-gpu')
# browser = webdriver.Chrome(chrome_options = option)
fireFoxOptions = webdriver.FirefoxOptions()
fireFoxOptions.set_headless()
browser = webdriver.Firefox(firefox_options=fireFoxOptions)
asserts_all=list()
mark_time = 0
last_value = 0
now_len = 0
pre_len = 0
count_all = 0
try:
for down_loading_url in down_loading_urls:
original_url = "https://coolors.co/browser/best/{}".format(down_loading_url)
print("down_loading_url: ",original_url)
browser.get(original_url)
time.sleep(25)
pageSource = browser.page_source
soup = BeautifulSoup(pageSource,'lxml')
asserts = soup.find_all('div', {"class":"browser-palette-colors"})
for lines in asserts:
for line in lines.children:
if line.find("span") != -1:
color_value = line.find("span").get_text()
# print(color_value)
color_value = color_value.strip()
if color_value != None and color_value != "":
with open(temp_path,'a',encoding="utf-8") as w_file:
w_file.write(color_value + "\n")
asserts_all.append(color_value)
now_len = len(asserts_all)
print("now_len: ",now_len)
if pre_len == now_len:
print("error: ", original_url)
pre_len = now_len
except Exception as e:
print("global",e,original_url)
finally:
with open(path,'w',encoding="utf8") as write_file:
for line in asserts_all:
write_file.write(str(line)+"\n")
# pass
browser.close()
网友评论