🧐添加特定RSS地址配置项,提高爬取成功率

This commit is contained in:
2024-09-03 21:32:32 +08:00
parent bd8e7f0ab5
commit 9b11eb4a2e
7 changed files with 424 additions and 2204 deletions

3
run.py
View File

@ -14,8 +14,9 @@ if config["spider_settings"]["enable"]:
print("爬虫已启用")
json_url = config['spider_settings']['json_url']
article_count = config['spider_settings']['article_count']
specific_RSS = config['specific_RSS']
print("正在从 {json_url} 中获取,每个博客获取 {article_count} 篇文章".format(json_url=json_url, article_count=article_count))
result, lost_friends = fetch_and_process_data(json_url=json_url, count=article_count)
result, lost_friends = fetch_and_process_data(json_url=json_url, specific_RSS=specific_RSS, count=article_count)
if config["spider_settings"]["merge_result"]["enable"]:
marge_json_url = config['spider_settings']["merge_result"]['merge_json_url']
print("合并数据功能开启,从 {marge_json_url} 中获取境外数据并合并".format(marge_json_url=marge_json_url + "/all.json"))