diff --git a/中央党报/CrawlZhongguoqingnianbao.py b/中央党报/CrawlZhongguoqingnianbao.py new file mode 100644 index 0000000..781972e --- /dev/null +++ b/中央党报/CrawlZhongguoqingnianbao.py @@ -0,0 +1,298 @@ +# _*_ coding : UTF-8 _*_ +# @Time : 2025/02/07 22:33 +# @UpdateTime : 2025/02/07 22:33 +# @Author : sonder +# @File : CrawlZhongguoqingnianbao.py +# @Software : PyCharm +# @Comment : 本程序 + +import asyncio +import random +from datetime import datetime + +from bs4 import BeautifulSoup, Comment +from httpx import AsyncClient +from motor.motor_asyncio import AsyncIOMotorClient + +start_date = datetime.strptime('2011-01', '%Y-%m') +"""中国青年报2011-01开始有效数据""" +end_date = datetime.today() +"""截止到今天""" +headers = { + 'User-Agent': 'User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36 Edg/107.0.1418.42'} + +pattern = r']+)>]*>([^<]+)' +# 链接数据库 +client = AsyncIOMotorClient('mongodb://localhost:27017') +db = client['zydm'] +collection = db['zgqnb'] + + +async def main(): + collection_names = await db.list_collection_names() + # 判断数据表是否存在 + if "zgqnb" not in collection_names: + print("中国青年报数据表不存在，开始采集！") + await getData(start_date, end_date) + else: + # 如果存在，则从数据库中获取最后一条记录的日期 + last_record = await collection.find_one({}, sort=[('release_time', -1)]) + last_date_str = last_record['release_time'] + print("数据库截止时间:", last_date_str) + await getData(last_date_str, end_date) + + +async def getContent(soup: BeautifulSoup) -> str: + """ + :param soup: BeautifulSoup对象 + :return: 文章内容 + """ + content = "" + for p in soup.select("#ozoom p"): + para = p.text.strip() + if para: + content += para + content += '\n' + for p in soup.select("#content p"): + para = p.text.strip() + if para: + content += para + content += '\n' + return content + + +async def getData(start_date: datetime, end_date: datetime): + """ + :param start_date: 开始日期 + :param end_date: 结束日期 + :return: None + """ + crawl_num = 0 + # 创建一个列表保存月份 + months = [] + # 从开始日期到结束日期，每个月份都添加到列表中 + current_date = start_date + current_date = current_date.replace(day=1) + while current_date <= end_date: + months.append(current_date) + # 增加一个月 + if current_date.month == 12: + current_date = current_date.replace(year=current_date.year + 1, month=1) + else: + current_date = current_date.replace(month=current_date.month + 1) + # 遍历月份列表 + for month in months: + if month < datetime(2024, 12, 1): + # 构造URL + url = f'https://zqb.cyol.com/html/{month.strftime("%Y-%m")}/period.xml' + """https://zqb.cyol.com/html/2024-01/period.xml""" + print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url) + async with AsyncClient(headers=headers, timeout=60) as client: + response = await client.get(url) + response.encoding = response.charset_encoding + print(f"一级连接状态：{response.status_code}") + if response.status_code == 200: + soup = BeautifulSoup(response.text, 'xml') + for period in soup.select("period"): + period_name = datetime.strptime(period.find("period_name").text.strip(), "%Y-%m-%d") + front_page = period.find("front_page").text.strip() + try: + url1 = f"https://zqb.cyol.com/html/{period_name.strftime('%Y-%m/%d')}/{front_page}" + """https://zqb.cyol.com/html/2024-01/01/nbs.D110000zgqnb_01.htm""" + print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url1) + response2 = await client.get(url1) + response2.encoding = response2.charset_encoding + print(f"二级连接状态：{response2.status_code}") + if response2.status_code == 200: + soup2 = BeautifulSoup(response2.text, 'lxml') + for item in soup2.select("#pageLink"): + banmianming = item.text.split("：")[-1] + banmianhao = item.text.split("：")[0] + url2 = f"https://zqb.cyol.com/html/{period_name.strftime('%Y-%m/%d')}/" + item.get( + "href").replace("./", "").strip() + """https://zqb.cyol.com/html/2024-01/01/nbs.D110000zgqnb_01.htm""" + print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url2) + response3 = await client.get(url2) + response3.encoding = response3.charset_encoding + print(f"三级连接状态：{response3.status_code}") + if response3.status_code == 200: + soup3 = BeautifulSoup(response3.text, 'lxml') + for item2 in soup3.select("#titleList li a"): + url3 = f"https://zqb.cyol.com/html/{period_name.strftime('%Y-%m/%d')}/" + item2.get( + "href").replace( + "./", "").strip() + """https://zqb.cyol.com/html/2024-01/01/nw.D110000zgqnb_20240101_1-01.htm""" + if await collection.find_one({"detail_url": url3}, {"_id": False}): + continue + print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url3) + response4 = await client.get(url3) + response4.encoding = response4.charset_encoding + print(f"四级连接状态：{response4.status_code}") + if response4.status_code == 200: + soup4 = BeautifulSoup(response4.text, 'html.parser') + try: + comments = soup4.find_all( + string=lambda text: isinstance(text, Comment)) + for comment in comments: + if 'mpproperty' in comment: + enpproperty_content = comment.strip() + inner_soup = BeautifulSoup(enpproperty_content, + 'html.parser') + # 提取特定标签值 + title = inner_soup.find('title').text.strip() + perTitle = inner_soup.find( + 'founder-introtitle').text.strip() + subTitle = inner_soup.find("founder-subtitle").text.strip() + author = inner_soup.find('author').text.strip() + except: + title = title + perTitle = "" + subTitle = "" + author = "" + content = await getContent(soup4) + await collection.insert_one({ + "title": title, + "subtitle": subTitle, + "preTitle": perTitle, + "author": author, + "banmianming": banmianming, + "banmianhao": banmianhao, + 'detail_url': url3, + 'release_time': period_name, + 'insert_timestamp': datetime.today(), + 'content': content + }) + crawl_num += 1 + print( + f"中国青年报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}---{title}---采集完成！") + await asyncio.sleep(random.randint(5, 15)) + print( + f"中国青年报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}-----采集完成！") + await asyncio.sleep(random.randint(5, 15)) + print( + f"中国青年报---{period_name.strftime('%Y-%m-%d')}------采集完成！") + await asyncio.sleep(random.randint(5, 15)) + except Exception as e: + print(e) + await collection.insert_one( + {'banmianhao': 'empty', + 'banmianming': 'empty', + 'preTitle': 'empty', + 'title': 'empty', + 'subtitle': 'empty', + 'author': 'empty', + 'detail_url': url, + 'release_time': period_name, + 'insert_timestamp': datetime.today(), + 'content': 'empty'} + ) + else: + # 构造URL + url = f'https://zqb.cyol.com/pc/layout/{month.strftime("%Y%m")}/period.xml' + """https://zqb.cyol.com/pc/layout/202501/period.xml""" + print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url) + async with AsyncClient(headers=headers, timeout=60) as client: + response = await client.get(url) + response.encoding = response.charset_encoding + print(f"一级连接状态：{response.status_code}") + if response.status_code == 200: + soup = BeautifulSoup(response.text, 'xml') + for period in soup.select("period"): + period_name = datetime.strptime(period.find("period_name").text.strip(), "%Y-%m-%d") + front_page = period.find("front_page").text.strip() + try: + url1 = f"https://zqb.cyol.com/pc/layout/{period_name.strftime('%Y%m/%d')}/{front_page}" + """https://zqb.cyol.com/pc/layout/202502/07/node_01.html""" + print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url1) + response2 = await client.get(url1) + response2.encoding = response2.charset_encoding + print(f"二级连接状态：{response2.status_code}") + if response2.status_code == 200: + soup2 = BeautifulSoup(response2.text, 'lxml') + for item in soup2.select("#pageLink"): + banmianming = item.text.split("：")[-1] + banmianhao = item.text.split("：")[0] + url2 = f"https://zqb.cyol.com/pc/layout/{period_name.strftime('%Y%m/%d')}/" + item.get( + "href").replace("./", "").strip() + """https://zqb.cyol.com/pc/layout/202502/07/node_01.html""" + print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url2) + response3 = await client.get(url2) + response3.encoding = response3.charset_encoding + print(f"三级连接状态：{response3.status_code}") + if response3.status_code == 200: + soup3 = BeautifulSoup(response3.text, 'lxml') + for item2 in soup3.select(".news-list a"): + url3 = f"https://zqb.cyol.com/pc/" + item2.get( + "href").replace( + "../", "").strip() + """https://zqb.cyol.com/pc/content/202502/07/content_406551.html""" + if await collection.find_one({"detail_url": url3}, {"_id": False}): + continue + title = item2.text.strip() + print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url3) + response4 = await client.get(url3) + response4.encoding = response4.charset_encoding + print(f"四级连接状态：{response4.status_code}") + if response4.status_code == 200: + soup4 = BeautifulSoup(response4.text, 'html.parser') + try: + comments = soup4.find_all( + string=lambda text: isinstance(text, Comment)) + for comment in comments: + if 'enpproperty' in comment: + # 提取注释内容 + enpproperty_content = comment.strip() + inner_soup = BeautifulSoup(enpproperty_content, + 'html.parser') + # 提取特定标签值 + title = inner_soup.find('title').text.strip() + perTitle = inner_soup.find('introtitle').text.strip() + subTitle = inner_soup.find("subtitle").text.strip() + author = inner_soup.find('author').text.strip() + except: + title = title + perTitle = "" + subTitle = "" + author = "" + content = await getContent(soup4) + await collection.insert_one({ + "title": title, + "subtitle": subTitle, + "preTitle": perTitle, + "author": author, + "banmianming": banmianming, + "banmianhao": banmianhao, + 'detail_url': url3, + 'release_time': period_name, + 'insert_timestamp': datetime.today(), + 'content': content + }) + crawl_num += 1 + print( + f"中国青年报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}---{title}---采集完成！") + await asyncio.sleep(random.randint(5, 15)) + print( + f"中国青年报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}-----采集完成！") + await asyncio.sleep(random.randint(5, 15)) + print( + f"中国青年报---{period_name.strftime('%Y-%m-%d')}------采集完成！") + await asyncio.sleep(random.randint(5, 15)) + except Exception as e: + print(e) + await collection.insert_one( + {'banmianhao': 'empty', + 'banmianming': 'empty', + 'preTitle': 'empty', + 'title': 'empty', + 'subtitle': 'empty', + 'author': 'empty', + 'keywordlist': 'empty', + 'detail_url': url, + 'release_time': period_name, + 'insert_timestamp': datetime.today(), + 'content': 'empty'} + ) + print(f"中国青年报采集完毕，共采集{crawl_num}条数据！") + + +asyncio.run(main())