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 asyncio
|
||||||
import random
|
import random
|
||||||
from datetime import datetime, timedelta
|
from datetime import datetime
|
||||||
|
|
||||||
from bs4 import BeautifulSoup
|
from bs4 import BeautifulSoup
|
||||||
from httpx import AsyncClient
|
from httpx import AsyncClient
|
||||||
@ -20,8 +20,8 @@ start_date = datetime.strptime('2017-09', '%Y-%m')
|
|||||||
end_date = datetime.today()
|
end_date = datetime.today()
|
||||||
"""截止到今天"""
|
"""截止到今天"""
|
||||||
headers = {
|
headers = {
|
||||||
"connection":'keep-alive',
|
"connection": 'keep-alive',
|
||||||
"host":"rmydb.cnii.com.cn",
|
"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'}
|
'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
|
# 链接数据库
|
||||||
@ -67,82 +67,87 @@ async def getData(start_date: datetime, end_date: datetime):
|
|||||||
"""
|
"""
|
||||||
crawl_num = 0
|
crawl_num = 0
|
||||||
start_date = int(start_date.strftime("%Y%m%d"))
|
start_date = int(start_date.strftime("%Y%m%d"))
|
||||||
async with AsyncClient(headers=headers, timeout=60) as client:
|
try:
|
||||||
response = await client.get("https://rmydb.cnii.com.cn/period/yearMonthDay.json")
|
async with AsyncClient(headers=headers, timeout=60) as client:
|
||||||
response.encoding = response.charset_encoding
|
response = await client.get("https://rmydb.cnii.com.cn/period/yearMonthDay.json")
|
||||||
print(f"一级连接状态：{response.status_code}")
|
response.encoding = response.charset_encoding
|
||||||
if response.status_code == 200:
|
print(f"一级连接状态：{response.status_code}")
|
||||||
data = response.json()
|
if response.status_code == 200:
|
||||||
dayList = []
|
data = response.json()
|
||||||
for value in data.values():
|
dayList = []
|
||||||
for item in value.values():
|
for value in data.values():
|
||||||
dayList += item
|
for item in value.values():
|
||||||
dayList.sort()
|
dayList += item
|
||||||
dayList = list(filter(lambda x: x >= start_date, list(map(int, dayList))))
|
dayList.sort()
|
||||||
for day in dayList:
|
dayList = list(filter(lambda x: x >= start_date, list(map(int, dayList))))
|
||||||
try:
|
for day in dayList:
|
||||||
url = f"https://rmydb.cnii.com.cn/html/{day.__str__()[:4]}/{day}/data.json"
|
try:
|
||||||
print(url)
|
url = f"https://rmydb.cnii.com.cn/html/{day.__str__()[:4]}/{day}/data.json"
|
||||||
response = await client.get(url)
|
print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url)
|
||||||
response.encoding = response.charset_encoding
|
response = await client.get(url)
|
||||||
print(f"二级连接状态：{response.status_code}")
|
response.encoding = response.charset_encoding
|
||||||
if response.status_code == 200:
|
print(f"二级连接状态：{response.status_code}")
|
||||||
data = response.json()
|
if response.status_code == 200:
|
||||||
for item in data:
|
data = response.json()
|
||||||
banmianming = item["pageName"]
|
for item in data:
|
||||||
banmianhao = f"第{item['pageNo']}版"
|
banmianming = item["pageName"]
|
||||||
for article in item["onePageArticleList"]:
|
banmianhao = f"第{item['pageNo']}版"
|
||||||
title = article["mainTitle"]
|
for article in item["onePageArticleList"]:
|
||||||
url2 = f"https://rmydb.cnii.com.cn/html/{day.__str__()[:4]}/{day}/{day}_{item['pageNo']}/{article['articleHref']}"
|
title = article["mainTitle"]
|
||||||
"""https://rmydb.cnii.com.cn/html/2024/20240906/20240906_001/20240906_001_01_523.html"""
|
url2 = f"https://rmydb.cnii.com.cn/html/{day.__str__()[:4]}/{day}/{day}_{item['pageNo']}/{article['articleHref']}"
|
||||||
author = article["articleAuthor"]
|
"""https://rmydb.cnii.com.cn/html/2024/20240906/20240906_001/20240906_001_01_523.html"""
|
||||||
if await collection.find_one({"detail_url": url2}, {"_id": False}):
|
author = article["articleAuthor"]
|
||||||
continue
|
if await collection.find_one({"detail_url": url2}, {"_id": False}):
|
||||||
print(url2)
|
continue
|
||||||
response2 = await client.get(url2)
|
print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url2)
|
||||||
response2.encoding = response2.charset_encoding
|
response2 = await client.get(url2)
|
||||||
print(f"三级连接状态：{response2.status_code}")
|
response2.encoding = response2.charset_encoding
|
||||||
if response2.status_code == 200:
|
print(f"三级连接状态：{response2.status_code}")
|
||||||
soup = BeautifulSoup(response2.text, "lxml")
|
if response2.status_code == 200:
|
||||||
preTitle = soup.select_one("#PreTitle").text
|
soup = BeautifulSoup(response2.text, "lxml")
|
||||||
title = soup.select_one("#Title").text
|
preTitle = soup.select_one("#PreTitle").text
|
||||||
subTitle = soup.select_one("#SubTitle").text
|
title = soup.select_one("#Title").text
|
||||||
content = await getContent(soup)
|
subTitle = soup.select_one("#SubTitle").text
|
||||||
await collection.insert_one({
|
content = await getContent(soup)
|
||||||
"title": title,
|
await collection.insert_one({
|
||||||
"subtitle": subTitle,
|
"title": title,
|
||||||
"preTitle": preTitle,
|
"subtitle": subTitle,
|
||||||
"author": author,
|
"preTitle": preTitle,
|
||||||
"banmianming": banmianming,
|
"author": author,
|
||||||
"banmianhao": banmianhao,
|
"banmianming": banmianming,
|
||||||
'keywordlist': "empty",
|
"banmianhao": banmianhao,
|
||||||
'detail_url': url2,
|
'keywordlist': "empty",
|
||||||
'release_time': datetime.strptime(str(day), "%Y%m%d"),
|
'detail_url': url2,
|
||||||
'insert_timestamp': datetime.today(),
|
'release_time': datetime.strptime(str(day), "%Y%m%d"),
|
||||||
'content': content
|
'insert_timestamp': datetime.today(),
|
||||||
})
|
'content': content
|
||||||
crawl_num += 1
|
})
|
||||||
print(f"人民邮电报---{day}---{banmianming}---{banmianhao}---{title}---采集完成！")
|
crawl_num += 1
|
||||||
await asyncio.sleep(random.randint(5, 15))
|
print(
|
||||||
print(f"人民邮电报---{day}---{banmianming}---{banmianhao}-----采集完成！")
|
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))
|
await asyncio.sleep(random.randint(5, 15))
|
||||||
print(f"人民邮电报---{day}-----采集完成！")
|
except Exception as e:
|
||||||
await asyncio.sleep(random.randint(5, 15))
|
print(e)
|
||||||
except Exception as e:
|
await collection.insert_one(
|
||||||
print(e)
|
{'banmianhao': 'empty',
|
||||||
await collection.insert_one(
|
'banmianming': 'empty',
|
||||||
{'banmianhao': 'empty',
|
'preTitle': 'empty',
|
||||||
'banmianming': 'empty',
|
'title': 'empty',
|
||||||
'preTitle': 'empty',
|
'subtitle': 'empty',
|
||||||
'title': 'empty',
|
'author': 'empty',
|
||||||
'subtitle': 'empty',
|
'keywordlist': 'empty',
|
||||||
'author': 'empty',
|
'detail_url': url,
|
||||||
'keywordlist': 'empty',
|
'release_time': datetime.strptime(str(day), "%Y%m%d"),
|
||||||
'detail_url': url,
|
'insert_timestamp': datetime.today(),
|
||||||
'release_time': datetime.strptime(str(day), "%Y%m%d"),
|
'content': 'empty'}
|
||||||
'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！")
|
print(f"人民邮电报采集完毕，共采集{crawl_num}条数据！")
|
||||||
|
|
||||||
|
|
||||||
asyncio.run(main())
|
asyncio.run(main())
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user