Python爬取百度搜索結果頁面並輸出標題和鏈接

# 爬取百度10頁的標題

import urllib.request
import re
import urllib.parse
from bs4 import BeautifulSoup

def build_onepage_crawl_function(keyword, number_of_page):
    #構建請求頭
    user_agent_header = ("User-Agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:78.0) Gecko/20100101 Firefox/78.0)")
    opener_build = urllib.request.build_opener()
    opener_build.addheaders = [user_agent_header]
    #對搜索關鍵詞進行編碼
    encoded_keyword = urllib.parse.quote(keyword) 
    # 通過for循環爬去每一頁
    for i in range(int(number_of_page)):
        url = "https://www.baidu.com"
        number_of_page = i * 10 # 構造 &pn=
        print("百度搜索頁面鏈接:",number_of_page)
        url = url + "/s?wd=" + encoded_keyword + "&pn=" + str(number_of_page) # 完整的url包括關鍵詞說頁數,這裏keyword本身就是str
        print(url)
        #構造get請求中的url
        original_html = opener_build.open(url, timeout = 2).read().decode("utf-8","ignore")
        soup = BeautifulSoup(original_html ,'html.parser')
        for title in soup.select('.tts-title a'):
            print(title.text)
    
#輸入關鍵詞以及需要爬取的頁數
keyword_input = input("請輸入關鍵詞：")
number_of_page_input = input("請輸入頁數：")
build_onepage_crawl_function(keyword_input, number_of_page_input)