hygc/guoneimeitishujucaiji
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: 添加中国民族报，科技日报，人民邮电报

Browse Source
This commit is contained in:
皓月归尘 2024-11-10 00:17:12 +08:00
parent 3bfb57b662
commit 4cb5d4a5d3
5 changed files with 496 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

199
国内党媒/CrawlKejiribao.py Normal file
View File

@ -0,0 +1,199 @@
# _*_ coding : UTF-8 _*_
# @Time : 2024/11/10 21:23
# @UpdateTime : 2024/11/10 21:23
# @Author : haochen zhong
# @File : CrawlKejiribao.py
# @Software : PyCharm
# @Comment : 本程序采集科技日报数据
import asyncio
import random
from datetime import datetime
from bs4 import BeautifulSoup
from httpx import AsyncClient
from motor.motor_asyncio import AsyncIOMotorClient
start_date = datetime.strptime('2011-01', '%Y-%m')
"""科技日报报2011年1月份开始有数据"""
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'}
# 链接数据库
client = AsyncIOMotorClient('mongodb://localhost:27017')
db = client['buweijiguanbao']
collection = db['kejiribao']
async def main():
collection_names = await db.list_collection_names()
# 判断数据表是否存在
if "kejiribao" not in collection_names:
# 如果不存在，则从2017年9月开始爬取
print("科技日报数据表不存在，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'
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
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:
# 构造URL
url = f'https://digitalpaper.stdaily.com/http_www.kjrb.com/kjrb/html/{month.strftime("%Y-%m")}/period.xml'
"""https://digitalpaper.stdaily.com/http_www.kjrb.com/kjrb/html/2011-10/period.xml"""
print(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.select_one("period_name").text.strip(), "%Y-%m-%d")
front_page = period.select_one("front_page").text.strip()
try:
url1 = f"https://digitalpaper.stdaily.com/http_www.kjrb.com/kjrb/html/{period_name.strftime('%Y-%m/%d')}/{front_page}"
"""https://digitalpaper.stdaily.com/http_www.kjrb.com/kjrb/html/2024-10/30/node_2.htm"""
print(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://digitalpaper.stdaily.com/http_www.kjrb.com/kjrb/html/{period_name.strftime('%Y-%m/%d')}/" + item.get(
"href").replace("./", "").strip()
print(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')
pages = soup3.select(".ul02_l a")
if pages:
titleTag = "body > table:nth-child(2) > tbody > tr:nth-child(1) > td:nth-child(2) > table:nth-child(3) > tbody > tr:nth-child(1) > td > table > tbody > tr > td > strong"
subTitleTag = "body > table:nth-child(2) > tbody > tr:nth-child(1) > td:nth-child(2) > table:nth-child(3) > tbody > tr:nth-child(1) > td > table > tbody > tr > td > span:nth-child(5)"
preTitleTag = "body > table:nth-child(2) > tbody > tr:nth-child(1) > td:nth-child(2) > table:nth-child(3) > tbody > tr:nth-child(1) > td > table > tbody > tr > td > span:nth-child(1)"
authorTag = "body > table:nth-child(2) > tbody > tr:nth-child(1) > td:nth-child(2) > table:nth-child(3) > tbody > tr:nth-child(1) > td > table > tbody > tr > td > span:nth-child(7)"
else:
pages = soup3.select(".title a")
titleTag = ".biaoti"
subTitleTag = ".futi"
preTitleTag = ".yinti"
authorTag = ".autor"
for item2 in pages:
url3 = f"https://digitalpaper.stdaily.com/http_www.kjrb.com/kjrb/html/{period_name.strftime('%Y-%m/%d')}/" + item2.get(
"href")
"""https://digitalpaper.stdaily.com/http_www.kjrb.com/kjrb/html/2024-10/30/content_579753.htm?div=-1"""
if await collection.find_one({"detail_url": url3}, {"_id": False}):
continue
title = item2.text.strip()
print(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, 'lxml')
try:
title = soup4.select_one(titleTag).text.strip()
except:
title = title
try:
subTitle = soup4.select(subTitleTag)[0].text.strip()
except:
subTitle = ""
try:
author = soup4.select_one(authorTag).text.strip()
except:
author = ""
try:
perTitle = soup4.select(preTitleTag)[-1].text.strip()
except:
perTitle = ""
try:
keywordlist = soup4.find("founder-keyword").text.strip()
except:
keywordlist = ""
content = await getContent(soup4)
await collection.insert_one({
"title": title,
"subtitle": subTitle,
"preTitle": perTitle,
"author": author,
"banmianming": banmianming,
"banmianhao": banmianhao,
'keywordlist': keywordlist,
'detail_url': url3,
'release_time': period_name,
'insert_timestamp': datetime.today(),
'content': content
})
crawl_num += 1
print(
f"科技日报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}---{title}---采集完成！")
await asyncio.sleep(random.randint(5, 15))
print(
f"科技日报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}-----采集完成！")
await asyncio.sleep(random.randint(5, 15))
print(f"科技日报---{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"科技日报采集完毕，共采集{crawl_num}条数据！")
asyncio.run(main())

148
国内党媒/CrawlRenminyoudianbao.py Normal file
View File

@ -0,0 +1,148 @@
# _*_ coding : UTF-8 _*_
# @Time : 2024/11/11 21:41
# @UpdateTime : 2024/11/11 21:41
# @Author : haochen zhong
# @File : CrawlRenminyoudianbao.py
# @Software : PyCharm
# @Comment : 本程序采集人民邮电报
import asyncio
import random
from datetime import datetime, timedelta
from bs4 import BeautifulSoup
from httpx import AsyncClient
from motor.motor_asyncio import AsyncIOMotorClient
start_date = datetime.strptime('2017-09', '%Y-%m')
"""中国改革报2017年9月份开始有数据"""
end_date = datetime.today()
"""截止到今天"""
headers = {
"connection":'keep-alive',
"host":"rmydb.cnii.com.cn",
'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'}
# 链接数据库
client = AsyncIOMotorClient('mongodb://localhost:27017')
db = client['buweijiguanbao']
collection = db['renminyoudianbao']
async def main():
collection_names = await db.list_collection_names()
# 判断数据表是否存在
if "renminyoudianbao" not in collection_names:
# 如果不存在，则从2017年9月开始爬取
print("人民邮电报数据表不存在，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'
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
start_date = int(start_date.strftime("%Y%m%d"))
async with AsyncClient(headers=headers, timeout=60) as client:
response = await client.get("https://rmydb.cnii.com.cn/period/yearMonthDay.json")
response.encoding = response.charset_encoding
print(f"一级连接状态：{response.status_code}")
if response.status_code == 200:
data = response.json()
dayList = []
for value in data.values():
for item in value.values():
dayList += item
dayList.sort()
dayList = list(filter(lambda x: x >= start_date, list(map(int, dayList))))
for day in dayList:
try:
url = f"https://rmydb.cnii.com.cn/html/{day.__str__()[:4]}/{day}/data.json"
print(url)
response = await client.get(url)
response.encoding = response.charset_encoding
print(f"二级连接状态：{response.status_code}")
if response.status_code == 200:
data = response.json()
for item in data:
banmianming = item["pageName"]
banmianhao = f"第{item['pageNo']}版"
for article in item["onePageArticleList"]:
title = article["mainTitle"]
url2 = f"https://rmydb.cnii.com.cn/html/{day.__str__()[:4]}/{day}/{day}_{item['pageNo']}/{article['articleHref']}"
"""https://rmydb.cnii.com.cn/html/2024/20240906/20240906_001/20240906_001_01_523.html"""
author = article["articleAuthor"]
if await collection.find_one({"detail_url": url2}, {"_id": False}):
continue
print(url2)
response2 = await client.get(url2)
response2.encoding = response2.charset_encoding
print(f"三级连接状态：{response2.status_code}")
if response2.status_code == 200:
soup = BeautifulSoup(response2.text, "lxml")
preTitle = soup.select_one("#PreTitle").text
title = soup.select_one("#Title").text
subTitle = soup.select_one("#SubTitle").text
content = await getContent(soup)
await collection.insert_one({
"title": title,
"subtitle": subTitle,
"preTitle": preTitle,
"author": author,
"banmianming": banmianming,
"banmianhao": banmianhao,
'keywordlist': "empty",
'detail_url': url2,
'release_time': datetime.strptime(str(day), "%Y%m%d"),
'insert_timestamp': datetime.today(),
'content': content
})
crawl_num += 1
print(f"人民邮电报---{day}---{banmianming}---{banmianhao}---{title}---采集完成！")
await asyncio.sleep(random.randint(5, 15))
print(f"人民邮电报---{day}---{banmianming}---{banmianhao}-----采集完成！")
await asyncio.sleep(random.randint(5, 15))
print(f"人民邮电报---{day}-----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': datetime.strptime(str(day), "%Y%m%d"),
'insert_timestamp': datetime.today(),
'content': 'empty'}
)
print(f"人民邮电报采集完毕，共采集{crawl_num}条数据！")
asyncio.run(main())

4
国内党媒/CrawlZhongguogaigebao.py
View File

@ -37,7 +37,7 @@ async def main():
# 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)
print("数据库截止时间:", last_date_str)
await getData(last_date_str, end_date)
@ -151,7 +151,7 @@ async def getData(start_date: datetime, end_date: datetime):
"banmianhao": banmianhao,
'keywordlist': keyword,
'detail_url': url3,
'release_time': month + timedelta(days=int(period_id)-1),
'release_time': month + timedelta(days=int(period_id) - 1),
'insert_timestamp': datetime.today(),
'content': content
})

9
国内党媒/CrawlZhongguojiaoyubao.py
View File

@ -8,7 +8,7 @@
import asyncio
import random
from datetime import datetime, timedelta
from datetime import datetime
from bs4 import BeautifulSoup
from httpx import AsyncClient
@ -101,7 +101,7 @@ async def getData(start_date: datetime, end_date: datetime):
banmianming = item.text.split("：")[-1]
banmianhao = item.text.split("：")[0]
url2 = f"http://paper.jyb.cn/zgjyb/html/{period_name.strftime('%Y-%m/%d')}/" + item.get(
"href").replace("./","").strip()
"href").replace("./", "").strip()
print(url2)
response3 = await client.get(url2)
response3.encoding = response3.charset_encoding
@ -201,7 +201,7 @@ async def getData(start_date: datetime, end_date: datetime):
banmianming = item.text.split(":")[-1]
banmianhao = item.text.split(":")[0]
url2 = f"http://paper.jyb.cn/zgjyb/html/{period_name.strftime('%Y-%m/%d')}/" + item.get(
"href").replace("./","").strip()
"href").replace("./", "").strip()
print(url2)
response3 = await client.get(url2)
response3.encoding = response3.charset_encoding
@ -273,10 +273,11 @@ async def getData(start_date: datetime, end_date: datetime):
'author': 'empty',
'keywordlist': 'empty',
'detail_url': url,
'release_time':period_name ,
'release_time': period_name,
'insert_timestamp': datetime.today(),
'content': 'empty'}
)
print(f"中国教育报采集完毕，共采集{crawl_num}条数据！")
asyncio.run(main())

142
国内党媒/CrawlZhongguominzubao.py Normal file
View File

@ -0,0 +1,142 @@
# _*_ coding : UTF-8 _*_
# @Time : 2024/11/12 22:45
# @UpdateTime : 2024/11/12 22:45
# @Author : haochen zhong
# @File : CrawlZhongguominzubao.py
# @Software : PyCharm
# @Comment : 本程序采集中国民族报数据
import asyncio
import random
from datetime import datetime
from bs4 import BeautifulSoup
from httpx import AsyncClient
from motor.motor_asyncio import AsyncIOMotorClient
start_date = datetime.strptime('2022-01', '%Y-%m')
"""中国民族报2022年1月份开始有数据"""
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'}
# 链接数据库
client = AsyncIOMotorClient('mongodb://localhost:27017')
db = client['buweijiguanbao']
collection = db['zhongguominzubao']
async def main():
collection_names = await db.list_collection_names()
# 判断数据表是否存在
if "zhongguomizubao" not in collection_names:
# 如果不存在，则从2017年9月开始爬取
print("中国民族数据表不存在，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 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
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
async with AsyncClient(headers=headers, timeout=60) as client:
for month in months:
# 构造URL
url = "http://210.12.104.26:81/reader/layout/getSZBDatePub.do"
try:
response = await client.post(url, params={"sj": month.strftime("%Y.%m")})
response.encoding = response.charset_encoding
print(f"一级连接状态：{response.status_code}")
if response.status_code == 200:
data = response.json()
for item in data:
url2 = "http://210.12.104.26:81/reader/layout/findBmMenuPub.do"
response2 = await client.post(url2, params={"docPubTime": item.replace("/", "")})
response2.encoding = response2.charset_encoding
print(f"二级连接状态：{response2.status_code}")
if response2.status_code == 200:
data2 = response2.json()
for item2 in data2:
banmianming = item2["BM"]
banmianhao = item2["BC"]
url3 = f"http://210.12.104.26:81/reader/layout/getBmDetailPub.do?bc={item2['IRCATELOG']}&docpubtime={item.replace('/', '')}"
print(url3)
response3 = await client.get(url3)
response3.encoding = response3.charset_encoding
print(f"三级连接状态：{response3.status_code}")
if response3.status_code == 200:
data3 = response3.json()
for item3 in data3:
url4 = "http://210.12.104.26:81/reader/layout/detailData.do"
response4 = await client.post(url4, params={"guid": item3['ZB_GUID']})
response4.encoding = response4.charset_encoding
print(f"四级连接状态：{response4.status_code}")
if response4.status_code == 200:
data4 = response4.json()
title = BeautifulSoup(data4['docTitle'],"lxml").text
subTitle = BeautifulSoup(data4['fb'],"lxml").text
preTitle = BeautifulSoup(data4['yt'],"lxml").text
author = data4['docAuthor']
content = BeautifulSoup(data4["content"], "lxml").text
await collection.insert_one({
"title": title,
"subtitle": subTitle,
"preTitle": preTitle,
"author": author,
"banmianming": banmianming,
"banmianhao": banmianhao,
'keywordlist': "empty",
'detail_url': f"http://210.12.104.26:81/epaper/?id={item3['ZB_GUID']}&time={item.replace('/', '')}",
'release_time': datetime.strptime(data4["docPubTime"],
"%Y/%m/%d %H:%M:%S"),
'insert_timestamp': datetime.today(),
'content': content
})
crawl_num += 1
print(
f"中国民族报---{item}---{banmianming}---{banmianhao}---{title}---采集完成！")
await asyncio.sleep(random.randint(5, 15))
print(f"中国民族报---{item}---{banmianming}---{banmianhao}-----采集完成！")
await asyncio.sleep(random.randint(5, 15))
print(f"中国民族报---{item}----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': month,
'insert_timestamp': datetime.today(),
'content': 'empty'}
)
asyncio.run(main())