"""
百度搜索可視化
"""
import tkinter
 
import win32api
from selenium.webdriver import Chrome
 
entry = None
 
 
def callback():
    global entry
    keywords = entry.get()
    if not keywords:
        win32api.MessageBox(0, '請(qǐng)輸入搜索關(guān)鍵字', '提示', 0)
        return
    chrome = Chrome()
    chrome.get('https://www.baidu.com/')
    chrome.find_element_by_id('kw').send_keys(keywords)
    chrome.find_element_by_id('su').click()
 
    # bilibili關(guān)鍵字搜索
    # chrome.get('https://www.bilibili.com/')
    # chrome.find_element_by_xpath('//form[@id="nav_searchform"]/input').send_keys(keywords)
    # chrome.find_element_by_xpath('//div[@class="nav-search-btn"]/button').click()
 
 
def main():
    global entry
    tk = tkinter.Tk()
    # tk.resizable(width=False,height=False)  # 固定窗體大小?無(wú)效
    tk.title('百度搜索')
 
    # 1.設(shè)置窗體居中
    # screenwidth = tk.winfo_screenwidth()  # 獲取屏幕寬度
    # screenheight = tk.winfo_screenheight()  # 獲取屏幕高度
    # # 計(jì)算窗體大小,位置參數(shù),width,height:窗體寬高
    # width = 100
    # height = 50
    # size = '%dx%d+%d+%d' % (width, height, (screenwidth - width) / 2, (screenheight - height) / 2)
    # tk.geometry(size)  # 設(shè)置窗體位置為屏幕居中
 
    # 2.設(shè)置窗體右下角,無(wú)效
    # screenwidth = tk.winfo_screenwidth()  # 獲取屏幕寬度
    # screenheight = tk.winfo_screenheight()  # 獲取屏幕高度
    # print(screenwidth,screenheight)
    # # 計(jì)算窗體大小,位置參數(shù),width,height:窗體寬高
    # width = 100
    # height = 50
    # size = '%dx%d+%d+%d' % (width, height, (screenwidth - width), (screenheight - height))
    # tk.geometry(size)  # 設(shè)置窗體位置為屏幕右下角
 
    # 獲取窗體x,y
    # tk.update()
    # print(tk.winfo_x())
    # print(tk.winfo_y())
 
    tk.geometry('+0+0')  # 固定屏幕左上角
    # tk.geometry('+1440+770')
 
    entry = tkinter.Entry(tk)
    entry.pack()
 
    button = tkinter.Button(tk, text='百度一下', command=callback)
    button.pack()
 
    tk.mainloop()
 
 
if __name__ == '__main__':
    main()

# coding: utf-8
import os
import time
import requests
import urllib.parse
from bs4 import BeautifulSoup
from urllib.parse import urlparse
from fake_useragent import UserAgent
from multiprocessing.pool import ThreadPool
LOCATIONS = {}
GLOBAL_THREAD = 500
GLOBAL_TIMEOUT = 50
def get_links(keyword, generator, pages):
links = []
for page in range(int(pages.split("-")[0]), int(pages.split("-")[1]) + 1):
for genera in range(int(generator.split("-")[0]), int(generator.split("-")[1]) + 1):
links.append(
"http://www.baidu.com.cn/s?wd=" + urllib.parse.quote(keyword + str(genera)) + "&pn=" + str(page * 10))
return links
def get_page(url):
headers = {"user-agent": UserAgent().chrome}
req = requests.get(url, headers=headers)
req.encoding = "utf-8"
soup = BeautifulSoup(req.text, "lxml")
for link in soup.select("div.result > h3.t > a"):
req = requests.get(link.get("href"), headers=headers, allow_redirects=False)
if "=" in req.headers["location"]:
root = urlparse(req.headers["location"]).netloc
LOCATIONS[root] = req.headers["location"]
def baidu_search():
try:
os.system("cls")
print("-" * 56 + "\n")
print("| BaiduSearch Engine By 美圖博客[https://www.meitubk.com/] |\n")
print("-" * 56 + "\n")
keyword = input("Keyword: ")
generator = input("Generator(1-10): ")
pages = input("Pages(0-10): ")
start = time.time()
pool = ThreadPool(processes=GLOBAL_THREAD)
pool.map(get_page, get_links(keyword, generator, pages))
pool.close()
pool.join()
end = time.time()
path = r"D:\Desktop\result.txt"
save_result(path)
print("\nSava in %s" % path)
print("Result count: %d" % len(LOCATIONS.values()))
print("Running time: %ds" % (end - start))
except:
print("\nInput Error!")
exit(0)
def save_result(path):
with open(path, "w") as file:
for url in list(LOCATIONS.values()):
file.write(url + "\n")
baidu_search()