fix: 修复人民邮电报偶尔出现日期匹配失败问题
This commit is contained in:
parent
8d62f1d2db
commit
e134004f2d
@ -9,7 +9,7 @@
|
||||
|
||||
import asyncio
|
||||
import random
|
||||
from datetime import datetime, timedelta
|
||||
from datetime import datetime
|
||||
|
||||
from bs4 import BeautifulSoup
|
||||
from httpx import AsyncClient
|
||||
@ -20,8 +20,8 @@ start_date = datetime.strptime('2017-09', '%Y-%m')
|
||||
end_date = datetime.today()
|
||||
"""截止到今天"""
|
||||
headers = {
|
||||
"connection":'keep-alive',
|
||||
"host":"rmydb.cnii.com.cn",
|
||||
"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
|
||||
@ -67,82 +67,87 @@ async def getData(start_date: datetime, end_date: datetime):
|
||||
"""
|
||||
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！")
|
||||
try:
|
||||
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(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), 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(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), 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))
|
||||
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'}
|
||||
)
|
||||
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'}
|
||||
)
|
||||
except Exception as e:
|
||||
print(e)
|
||||
print(f"人民邮电报采集完毕，共采集{crawl_num}条数据！")
|
||||
|
||||
|
||||
asyncio.run(main())
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user