我想把采集到的数据保存到pdf中该怎么做

Question

"""
http://www.ccgp-hunan.gov.cn/page/notice/more.jsp

https://hunan.zcygov.cn/luban/announcement/list?utm=a0017.b0064.3.5.f7fcb4c03c7411ed84984b6678c33275
需求
1.招投标网站爬虫软件
2.需要有软件界面
3.可以选择下载保存公告文件
4.文件格式pdf
"""

import csv
import os
import PyPDF2
import requests
from lxml import etree
import json
from bs4 import BeautifulSoup
from pprint import pprint
url = 'http://www.ccgp-hunan.gov.cn/mvc/getNoticeList4Web.do'
headers = {
    'Accept': 'application/json, text/javascript, */*; q=0.01',
    'Accept-Language': 'zh-CN,zh;q=0.9',
    'Connection': 'keep-alive',
    'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
    # 'Cookie': 'JSESSIONID=BD97B12D61360D93BEC5912F62B0F8BC',
    'Origin': 'http://www.ccgp-hunan.gov.cn',
    'Referer': 'http://www.ccgp-hunan.gov.cn/page/notice/more.jsp',
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36',
    'X-Requested-With': 'XMLHttpRequest',
}
data = {
    'pType': '',
    'prcmPrjName': '',
    'prcmItemCode': '',
    'prcmOrgName': '',
    'startDate': '2023-01-01',
    'endDate': '2023-03-11',
    'prcmPlanNo': '',
    'page': '1',
    'pageSize': '18',
}
cookies = {
    'JSESSIONID': 'BD97B12D61360D93BEC5912F62B0F8BC',
}
resp = requests.post(url,headers=headers,data=data,cookies=cookies)
r = resp.text
response = json.loads(resp.text)
lis = response["rows"]
# soup = BeautifulSoup(r,'lxml')
# list = soup.find_all('tr')

print(lis)
data = []
for i in lis:
    # item = {}
    # # print(i)
    # item['名字'] = i['ORG_NAME']
    # item['公告'] = i['NOTICE_TITLE']
    # item['时间'] = i['NEWWORK_DATE']
    # # item['链接'] = i['href']
    # data.append(item)
    title = i['ORG_NAME']
    announcement = i['NOTICE_TITLE']
    time = i['NEWWORK_DATE']

# with open('kaohe.csv','w',encoding='utf-8-sig',newline='') as f:
# #     writer = csv.DictWriter(f,fieldnames=['名字','公告','时间'])
# #     writer.writeheader()
# #     writer.writerows(data)

Answer 1

安装PyPDF2库，可以在终端中使用以下命令：

pip install pypdf2

在代码中添加以下内容，将每条数据保存为一个PDF文件：

# 创建PDF文件对象
pdf = PyPDF2.PdfFileWriter()

# 遍历数据列表
for i in lis:
    # 获取数据项
    title = i['ORG_NAME']
    announcement = i['NOTICE_TITLE']
    time = i['NEWWORK_DATE']
    
    # 创建PDF页面对象
    page = PyPDF2.pdf.PageObject.createBlankPage(None, 72*11, 72*8.5)
    
    # 在页面上添加数据
    page.mergePage(PyPDF2.pdf.PageObject.createTextObject(None, title))
    page.mergePage(PyPDF2.pdf.PageObject.createTextObject(None, announcement))
    page.mergePage(PyPDF2.pdf.PageObject.createTextObject(None, time))
    
    # 将页面添加到PDF文件中
    pdf.addPage(page)
    
    # 保存PDF文件
    with open('data.pdf', 'wb') as f:
        pdf.write(f)

答案来自 https://www.wodianping.com/