|
|
import re
|
|
|
import requests
|
|
|
from lxml import etree
|
|
|
import time
|
|
|
from urllib.parse import quote
|
|
|
|
|
|
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"}
|
|
|
|
|
|
cookies = " buvid3=8231EFA3-C943-B46F-C28D-10CA6EB40DD180949infoc; CURRENT_FNVAL=4048; rpdid=|(JYYJ|u)luu0J'uYmkl~mY)k; buvid4=CA2A9538-3AB7-5FF0-1AD2-830935987DFB07953-024012212-75GkjfNGeaGAWMbBOvqWtQ%3D%3D; buvid_fp=f29e4e3ef42f7eb5eeb379115e870ad9; LIVE_BUVID=AUTO7217086875647310; PVID=2; b_nut=100; _uuid=7FDC1091C-5D99-24A8-4133-F89DFB510EA6531786infoc; header_theme_version=CLOSE; enable_web_push=DISABLE; bili_ticket=eyJhbGciOiJIUzI1NiIsImtpZCI6InMwMyIsInR5cCI6IkpXVCJ9.eyJleHAiOjE3MjY2NDk2NTcsImlhdCI6MTcyNjM5MDM5NywicGx0IjotMX0.3Z1vsF3Xzu2nPlPrZBCesXytvgQb_37-XNcBtrRlMzE; bili_ticket_expires=1726649597; bsource=search_bing; bmg_af_switch=1; bmg_src_def_domain=i1.hdslb.com; home_feed_column=4; SESSDATA=188e2907%2C1742055275%2C569b4%2A92CjDCOHUaxUkq_L5c6PfUab0-sYNi5nOwFET1z4H9q14EuO2HVsnxLmx1932gpvUQBgESVnFIY3lzUFJhZWxtY1N1d21POEc5bDRKRldVTlJSTDNWdG8ybkJSYmdGN3g3S2hjRk1uYzhSVEJUUkVOMThzb2Zfb0txZlUwbDNVdnZEM1h6UjJ6amhBIIEC; bili_jct=b1a79048046b927643ac32fe2ce260a0; DedeUserID=1986103749; DedeUserID__ckMd5=be6d80b5f24d01e0; browser_resolution=1220-150; sid=6jgymz8o; bp_t_offset_1986103749=977826403892330496; b_lsid=EF11D7E6_191FBE2F27F"
|
|
|
|
|
|
dic_cookies = {}
|
|
|
for i in cookies.split("; "):
|
|
|
dic_cookies[i.split("=")[0]] = i.split("=")[1]
|
|
|
|
|
|
def get_web_url(keyword, pages):#页面url
|
|
|
# 对关键词进行URL编码
|
|
|
keyword = quote(keyword) if keyword else "" # 确保keyword不为None
|
|
|
res = []
|
|
|
pages = int(pages)
|
|
|
# 当请求页数为0时，直接返回空列表
|
|
|
if pages <= 0:
|
|
|
return res
|
|
|
else:
|
|
|
# 构建基础URL
|
|
|
url = f"https://search.bilibili.com/video?keyword={keyword}&from_source=webtop_search&spm_id_from=333.1007&search_source=5"
|
|
|
# 根据页数构建完整的URL列表
|
|
|
for i in range(pages):
|
|
|
if i > 0:
|
|
|
url1 = f"{url}&page={i + 1}&o={i * 30}"
|
|
|
else:
|
|
|
url1 = url
|
|
|
res.append(url1)
|
|
|
return res
|
|
|
|
|
|
def get_videos_url(web_url):#获取当前页面的所有视频的url
|
|
|
videos_url = []
|
|
|
response = requests.get(web_url,headers=headers,cookies=dic_cookies)
|
|
|
e = etree.HTML(response.text)
|
|
|
# xpath定位
|
|
|
a = e.xpath('//div[@class="video-list row"]/div[not(contains(@class, "to_hide_md"))]/div[1]/div[2]/a[1]')
|
|
|
for element in a:
|
|
|
href = element.get('href') # 获取href属性
|
|
|
href1 = f"https:{href}"
|
|
|
videos_url.append(href1)
|
|
|
return videos_url
|
|
|
|
|
|
def get_danmu(video_id):
|
|
|
#打开视频页面，获取视频cid
|
|
|
response = requests.get(video_id, headers=headers)
|
|
|
video_cid = re.search(r'"cid":(\d*),', response.text).group(1)
|
|
|
#用现有链接获取弹幕
|
|
|
url_dm = f"https://comment.bilibili.com/{video_cid}.xml"
|
|
|
response_dm = requests.get(url_dm,headers=headers,cookies=dic_cookies)
|
|
|
if response_dm.status_code == 200:
|
|
|
response_dm.encoding = 'utf-8'
|
|
|
content = re.findall('<d p=".*?">(.*?)</d>', response_dm.text)
|
|
|
print("请求弹幕成功")
|
|
|
return content
|
|
|
else:
|
|
|
print("请求弹幕失败")
|
|
|
return []
|
|
|
|
|
|
def writeintxt (list,file_path):
|
|
|
with open(file_path, 'w', encoding='utf-8') as file:
|
|
|
for item in list:
|
|
|
file.write(f"{item}\n ")
|
|
|
|
