import requests from bs4 import BeautifulSoup import openpyxl

def get_related_keywords(keyword): url = 'https://www.baidu.com/s' params = { 'wd': keyword, 'rn': '10', 'tn': 'baidurt', 'ie': 'utf-8', 'rqlang': 'cn', 'rsv_dl': 'tb', 'rsv_srlang': 'cn', 'rsv_rq': 'off' } headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3' } res = requests.get(url, params=params, headers=headers) soup = BeautifulSoup(res.text, 'html.parser') related_keywords = [] for related in soup.select('.tip'): related_keywords.append(related.text.strip()) return related_keywords

def get_dropdown_keywords(keyword): url = 'https://www.baidu.com/sugrec' params = { 'prod': 'pc', 'wd': keyword, 'cb': 'window.baidu.sug' } headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3' } res = requests.get(url, params=params, headers=headers) soup = BeautifulSoup(res.text, 'html.parser') dropdown_keywords = [] for dropdown in soup.select('.suglist li'): dropdown_keywords.append(dropdown.text.strip()) return dropdown_keywords

def save_to_excel(data): wb = openpyxl.Workbook() ws = wb.active ws.append(['Keyword', 'Related Keywords', 'Dropdown Keywords']) for row in data: ws.append(row) wb.save('keywords.xlsx')

if name == 'main': keywords = ['Python', '数据分析', '机器学习'] data = [] for keyword in keywords: related_keywords = get_related_keywords(keyword) dropdown_keywords = get_dropdown_keywords(keyword) row = [keyword, ', '.join(related_keywords), ', '.join(dropdown_keywords)] data.append(row) save_to_excel(data)

修复以下代码实现自动检索和抓取百度下拉框搜索词和相关推荐词并将抓取到的下拉词和相关词记录到表格中:import requestsfrom bs4 import BeautifulSoupimport openpyxldef get_related_keywordskeyword url = httpswwwbaiducoms params = wd keyword

原文地址: https://www.cveoy.top/t/topic/baWX 著作权归作者所有。请勿转载和采集!

免费AI点我,无需注册和登录