将数据存入excel表格
filename = 'D:/学院课程父类及子类对应表格.xlsx'//表格名称+位置
wb = openpyxl.load_workbook(filename)//1.初始化
sheet_names = wb.sheetnames//获取excel表格中的所有表
for sheet_name in sheet_names://遍历该表
sheet = wb[sheet_name]//初始化该表
for i in range(2, sheet.max_row + 1):
blog_id = sheet.cell(i, 1).value
blog = get_blog(blog_id)
recommend_tags = get_recommend_tags(blog)
url = f"https://blog.csdn.net/{blog['username']}/article/details/{blog_id}"
sheet.cell(i, 2, url)//sheet.cell(行数,列数,值)为每个表格中的单元格赋值
wb.save(filename)//需要保存,否则即使程序执行成功后写入操作不会生效
带请求体的post请求
headers = {
}
result = requests.post(url=url,data=json.dumps(data),headers=headers).json()
result = result['data']['list']['推荐']
print(result)
提取html网页中的元素
import parsel
selector = parsel.Selector(response.text)
title = selector.css('.style_h1::text').get()
content_list = selector.css('#article>p::text').getall()
novel_name = selector.css('.novel_info_title h1::text').get()
novel_chapter_urls_list = selector.css('.chapter_list a::attr(href)').getall()
保存文件
title = title.replace('/','-')
with open('D:\迅雷下载《'+novel_name+'》'+title+'.txt',mode='w',encoding='utf-8') as f:
f.write(title)
f.write('\n')
f.write(content)
print(title,'保存成功')
将列表转成字符串的最好方法
content = '\n'.join(content_list)
to be continued…