1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
| import os
import shutil
import requests
import logging
from bs4 import BeautifulSoup
from datetime import datetime
from concurrent.futures import ThreadPoolExecutor
from pypdf import PdfWriter
logging.getLogger("pypdf").setLevel(logging.ERROR)
class RMRBDownloader:
def __init__(self, date_str, is_overseas=False):
self.date_str = date_str
self.is_overseas = is_overseas
self.type_code = "rmrbhwb" if is_overseas else "rmrb"
self.type_name = "海外版" if is_overseas else "国内版"
domain = "https://paper.people.com.cn"
path = f"{self.type_code}/pc/layout/{date_str[:6]}/{date_str[6:]}/node_01.html"
self.base_url = f"{domain}/{path}"
self.temp_dir = f"{self.date_str}-{self.type_code}-temp"
self.output_name = f"人民日报_{self.type_name}_{self.date_str}.pdf"
self.headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
}
def get_page_list(self):
try:
resp = requests.get(self.base_url, headers=self.headers, timeout=10)
resp.encoding = 'utf-8'
if resp.status_code == 404:
print(f"ℹ️ {self.type_name} 在 {self.date_str} 可能未出版 (404)。")
return []
if resp.status_code != 200:
print(f"❌ 访问出错，状态码: {resp.status_code}")
return []
soup = BeautifulSoup(resp.text, 'html.parser')
links = soup.select('.swiper-slide a#pageLink')
return [(l.text.strip(), requests.compat.urljoin(self.base_url, l.get('href'))) for l in links if l.get('href')]
except Exception as e:
print(f"解析导航页异常: {e}")
return []
def download_pdf(self, page_info):
name, url = page_info
try:
resp = requests.get(url, headers=self.headers, timeout=10)
resp.encoding = 'utf-8'
soup = BeautifulSoup(resp.text, 'html.parser')
pdf_btn = soup.select_one('.paper-bot a[href$=".pdf"]')
if pdf_btn:
pdf_url = requests.compat.urljoin(url, pdf_btn.get('href'))
idx = name.split('：')[0].replace('第', '').replace('版', '')
pdf_data = requests.get(pdf_url, headers=self.headers, timeout=30)
if pdf_data.status_code == 200:
with open(os.path.join(self.temp_dir, f"{idx}.pdf"), 'wb') as f:
f.write(pdf_data.content)
print(f"✅ [{self.type_name}] {name} 下载成功")
except Exception:
pass
def run(self):
if not os.path.exists(self.temp_dir):
os.makedirs(self.temp_dir)
pages = self.get_page_list()
if pages:
print(f"🚀 正在获取 {self.date_str} {self.type_name} 共 {len(pages)} 个版面...")
with ThreadPoolExecutor(max_workers=5) as executor:
executor.map(self.download_pdf, pages)
files = sorted([f for f in os.listdir(self.temp_dir) if f.endswith('.pdf')])
if files:
merger = PdfWriter()
for f in files:
merger.append(os.path.join(self.temp_dir, f))
merger.write(self.output_name)
merger.close()
print(f"✨ 合并完成: {self.output_name}")
if os.path.exists(self.temp_dir):
shutil.rmtree(self.temp_dir)
if __name__ == "__main__":
date_val = input("请输入日期 (YYYYMMDD，直接回车下载今日): ").strip()
if not date_val: date_val = datetime.now().strftime("%Y%m%d")
RMRBDownloader(date_val, is_overseas=False).run()
RMRBDownloader(date_val, is_overseas=True).run()
|
