Update python.py

main
ppfc5brxg 5 months ago
parent dd61f21354
commit e371d5fd1f

@ -7,20 +7,19 @@ from wordcloud import WordCloud
import matplotlib.pyplot as plt
query = "巴黎奥运会"
headers = {
"Cookie": "buvid3=F85083C9-B0B0-58EF-387E-9810D717FBD394717infoc; b_nut=1695630694; i-wanna-go-back=-1; b_ut=7; _uuid=4691069C1-57109-F951-5C2C-71061B15CAB9C93820infoc; buvid4=80C1A4DB-57B6-89F1-B7AB-7AE606C3BFB795506-023092516-b1nz50QSFWAVh9QAs1wBqg%3D%3D; DedeUserID=391260816; DedeUserID__ckMd5=874384c11cc311ca; hit-dyn-v2=1; rpdid=|(JlRYJ~Yk||0J'uYmlYJ|~mu; buvid_fp_plain=undefined; LIVE_BUVID=AUTO7816956505396915; is-2022-channel=1; enable_web_push=DISABLE; header_theme_version=CLOSE; FEED_LIVE_VERSION=V_WATCHLATER_PIP_WINDOW3; CURRENT_BLACKGAP=0; bp_video_offset_391260816=964407697698979840; CURRENT_FNVAL=4048; CURRENT_QUALITY=116; fingerprint=0caf6ff40a6d821a9253179cd16721cc; buvid_fp=daecdb2a27b0352be0af14099f69b721; bili_ticket=eyJhbGciOiJIUzI1NiIsImtpZCI6InMwMyIsInR5cCI6IkpXVCJ9.eyJleHAiOjE3MjU1MDk5MzUsImlhdCI6MTcyNTI1MDY3NSwicGx0IjotMX0.uE2PcZgAdDTBtqyfu7qsT_GKqNMsmsvjtdKYmeQ0eno; bili_ticket_expires=1725509875; SESSDATA=d4e31c61%2C1740843740%2Cc4b21%2A91CjBgFJe4MbiVSvKl_Z-oJcHfxPNmwxIX4iMw7S41V1DMuuAhaahCmSK6_p-xsyPHvC8SVi13bXN4RE40V2NCeGYwNWhYclNJckNfaGx4SzZydk05aE56ajdkS2dzZUVRWG9YeE5jbXFVdXF1aTZWTmxQZnRjZXZYaHJLU1dleElsRVczZG4wQW9RIIEC; bili_jct=f25b09f990746c712d4ef672d19e2628; PVID=1; sid=84brlx1u; home_feed_column=5; browser_resolution=2048-1018; bp_t_offset_391260816=973171033005621248; b_lsid=54110E26A_191BB365E57",
headers = {"Cookie": "buvid3=F85083C9-B0B0-58EF-387E-9810D717FBD394717infoc; b_nut=1695630694; i-wanna-go-back=-1; b_ut=7; _uuid=4691069C1-57109-F951-5C2C-71061B15CAB9C93820infoc; buvid4=80C1A4DB-57B6-89F1-B7AB-7AE606C3BFB795506-023092516-b1nz50QSFWAVh9QAs1wBqg%3D%3D; DedeUserID=391260816; DedeUserID__ckMd5=874384c11cc311ca; hit-dyn-v2=1; rpdid=|(JlRYJ~Yk||0J'uYmlYJ|~mu; buvid_fp_plain=undefined; LIVE_BUVID=AUTO7816956505396915; is-2022-channel=1; enable_web_push=DISABLE; header_theme_version=CLOSE; FEED_LIVE_VERSION=V_WATCHLATER_PIP_WINDOW3; CURRENT_BLACKGAP=0; bp_video_offset_391260816=964407697698979840; CURRENT_FNVAL=4048; CURRENT_QUALITY=116; fingerprint=0caf6ff40a6d821a9253179cd16721cc; buvid_fp=daecdb2a27b0352be0af14099f69b721; bili_ticket=eyJhbGciOiJIUzI1NiIsImtpZCI6InMwMyIsInR5cCI6IkpXVCJ9.eyJleHAiOjE3MjU1MDk5MzUsImlhdCI6MTcyNTI1MDY3NSwicGx0IjotMX0.uE2PcZgAdDTBtqyfu7qsT_GKqNMsmsvjtdKYmeQ0eno; bili_ticket_expires=1725509875; SESSDATA=d4e31c61%2C1740843740%2Cc4b21%2A91CjBgFJe4MbiVSvKl_Z-oJcHfxPNmwxIX4iMw7S41V1DMuuAhaahCmSK6_pxsyPHvC8SVi13bXN4RE40V2NCeGYwNWhYclNJckNfaGx4SzZydk05aE56ajdkS2dzZUVRWG9YeE5jbXFVdXF1aTZWTmxQZnRjZXZYaHJLU1dleElsRVczZG4wQW9RIIEC; bili_jct=f25b09f990746c712d4ef672d19e2628; PVID=1; sid=84brlx1u; home_feed_column=5; browser_resolution=2048-1018; bp_t_offset_391260816=973171033005621248; b_lsid=54110E26A_191BB365E57",
"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"
}
total_page = 10
page = 10
cid_pattern = re.compile(r'"cid":(\d+)')
total_cid_list = []
total_comment_dict = {}
cid_list = []
comment_dict = {}
bvid_pattern = re.compile(r'bvid:"(.*?)"')
def GetFirstBidUrl(): # 获取第一个视频的bid
return "https://search.bilibili.com/all?vt=82099157&keyword=2024%E5%B7%B4%E9%BB%8E%E5%A5%A5%E8%BF%90%E4%BC%9A&from_source=webtop_search&spm_id_from=333.1007&search_source=5&page=2&o=36"
def GetCid(): # 获取300个视频的 bvid
for page in range(1, total_page + 1):
if len(total_cid_list) >= 300:
for page in range(1, page + 1):
if len(cid_list) >= 300:
break
print(f"Processing page {page}...\n", )
start = time.time()
@ -40,7 +39,7 @@ def GetCid(): # 获取300个视频的 bvid
current_cid = cid_pattern.search(respons.text).group(1)
print(f"获取到第{len(total_cid_list) + 1}个cid:{current_cid}")
total_cid_list.append(current_cid)
if len(total_cid_list) >= 300:
if len(cid_list) >= 300:
break
# time.sleep(1)
end = time.time()
@ -48,8 +47,8 @@ def GetCid(): # 获取300个视频的 bvid
time.sleep(1)
def Getdanmu(): # 遍历所有视频的 cid获取对应弹幕
get_cid_index = 0
for cid in total_cid_list:
get_cid_index += 1
for cid in cid_list:
cid_index += 1
print(f"正在获取第{get_cid_index}个视频的弹幕")
DanMu_url = f"https://api.bilibili.com/x/v1/dm/list.so?oid={cid}"
respons = requests.get(DanMu_url, headers=headers)
@ -64,9 +63,9 @@ def Getdanmu(): # 遍历所有视频的 cid获取对应弹幕
current_comment_dict[danmu] = 1
for k, v in current_comment_dict.items():
if k in total_comment_dict:
total_comment_dict[k] += v
comment_dict[k] += v
else:
total_comment_dict[k] = v
comment_dict[k] = v
time.sleep(0.5)
# 在得到的弹幕里筛选与ai相关的弹幕
def Sortdanmu():
@ -92,7 +91,7 @@ def CreatWordCloud():
comment_text = ' '.join([((k + ' ') * v) for k, v in sorted_comment_dict.items()])
wordcloud = WordCloud(
font_path='C:/Windows/Fonts/simsun.ttc',
width=800, height=400,
width=2000, height=1000,
background_color='white',
).generate(comment_text)

Loading…
Cancel
Save