Update qqwry.py

main 2024-06-12
FW27623 2 years ago committed by GitHub
parent 46ba1b056b
commit 9b4c9ad636
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

@ -2,44 +2,57 @@ import re
import json import json
import requests import requests
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
import time
def get_link(url): def get_link(url, retries=3, delay=5):
headers = { headers = {
'Accept-Language': 'zh-CN,zh;q=0.9,en-CN;q=0.8,en;q=0.7,zh-TW;q=0.6', 'Accept-Language': 'zh-CN,zh;q=0.9,en-CN;q=0.8,en;q=0.7,zh-TW;q=0.6',
'Cookie': 'rewardsn=; wxtokenkey=777', 'Cookie': 'rewardsn=; wxtokenkey=777',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36' 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36'
} }
# 访问链接并从json中提取微信推文链接 for attempt in range(retries):
response = requests.get(url, headers=headers) try:
data = json.loads(response.text) response = requests.get(url, headers=headers)
article_list = data['getalbum_resp']['article_list'] response.raise_for_status()
data = json.loads(response.text)
article_list = data['getalbum_resp']['article_list']
for article in article_list: for article in article_list:
title = article['title'] title = article['title']
if "纯真IP库社区版更新" in title: if "纯真IP库社区版更新" in title:
link = article['url'] link = article['url']
zip_url = get_zip_url(link) zip_url = get_zip_url(link, retries, delay)
if zip_url: if zip_url:
return link return link
return None
except (requests.RequestException, ValueError) as e:
print(f"第{attempt+1}次请求失败:{e}")
if attempt < retries - 1:
time.sleep(delay)
return None return None
def get_zip_url(link): def get_zip_url(link, retries=3, delay=5):
# 访问微信推文链接并解析网页 for attempt in range(retries):
response = requests.get(link) try:
soup = BeautifulSoup(response.text, 'html.parser') response = requests.get(link)
response.raise_for_status()
soup = BeautifulSoup(response.text, 'html.parser')
# 提取文本中的zip链接,正则匹配以https://开头以.zip后缀的链接 content_div = soup.find('div', {'id': 'js_content'})
content_div = soup.find('div', {'id': 'js_content'}) if content_div is not None:
if content_div is not None: content = content_div.get_text()
content = content_div.get_text() zip_url = re.findall(r'https://.*?\.zip', content)
zip_url = re.findall(r'https://.*?\.zip', content) return zip_url
return zip_url else:
else: return None
return None except (requests.RequestException, ValueError) as e:
print(f"第{attempt+1}次请求失败:{e}")
if attempt < retries - 1:
time.sleep(delay)
return None
if __name__ == '__main__': if __name__ == '__main__':
# 从微信推文json数据中获得最新一期IP库的发布文章链接
url = 'https://mp.weixin.qq.com/mp/appmsgalbum?__biz=Mzg3Mzc0NTA3NA==&action=getalbum&album_id=2329805780276838401&f=json' url = 'https://mp.weixin.qq.com/mp/appmsgalbum?__biz=Mzg3Mzc0NTA3NA==&action=getalbum&album_id=2329805780276838401&f=json'
try: try:

Loading…
Cancel
Save