You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
55 lines
1.9 KiB
55 lines
1.9 KiB
import requests
|
|
from bs4 import BeautifulSoup
|
|
import pandas as pd
|
|
import time
|
|
def get_danmu(urls):
|
|
# 获取BV号
|
|
bv_id = []
|
|
for url in urls:
|
|
parts = url.split('/')
|
|
for part in parts:
|
|
if part.startswith('BV'):
|
|
bv_id.append(part)
|
|
#获取cid号
|
|
cids = []
|
|
for id in bv_id:
|
|
url = f"https://api.bilibili.com/x/player/pagelist?bvid={id}&jsonp=jsonp"
|
|
headers = {
|
|
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36 Edg/128.0.0.0"
|
|
}
|
|
response = requests.get(url,headers=headers)
|
|
time.sleep(0.5)
|
|
if response.status_code == 200:
|
|
data = response.json()
|
|
if data['code'] == 0 and data['data']:
|
|
cid = data['data'][0]['cid']
|
|
cids.append(cid)
|
|
print("cid",len(cids))
|
|
#获取弹幕数据
|
|
danmu_data = []
|
|
fail_count = 0
|
|
for id in cids:
|
|
url = f"https://api.bilibili.com/x/v1/dm/list.so?oid={id}"
|
|
headers = {
|
|
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36 Edg/128.0.0.0"
|
|
}
|
|
response = requests.get(url,headers=headers)
|
|
time.sleep(0.5)
|
|
if response.status_code != 200:
|
|
fail_count += 1
|
|
response.encoding = 'utf-8'
|
|
danmu_data.append(response.text)
|
|
print("danmu_data_html",len(danmu_data))
|
|
print("fail_count",fail_count)
|
|
#返回一个所有弹幕的list
|
|
all_danmu = []
|
|
for html in danmu_data:
|
|
soup = BeautifulSoup(html, 'html.parser')
|
|
for d in soup.find_all('d'):
|
|
all_danmu.append(d.get_text())
|
|
|
|
print("all_danmu",len(all_danmu))
|
|
df = pd.DataFrame({'danmu': all_danmu})
|
|
df.to_excel("all_danmu_data.xlsx", index=False,engine='openpyxl')
|
|
return all_danmu
|