爬取弹幕之代码

Get_Danmaku.py

@@ -0,0 +1,92 @@
+import time
+import re
+import requests
+
+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",
+    "Cookie":"buvid4=D16319A3-9CCF-7099-A512-0A135AD5785B47915-023052812-b1nz50QSFWB5YJLoC8St7Q%3D%3D; buvid_fp_plain=undefined; enable_web_push=DISABLE; header_theme_version=CLOSE; DedeUserID=5493983; DedeUserID__ckMd5=5158623efb606499; CURRENT_FNVAL=16; blackside_state=0; CURRENT_BLACKGAP=0; FEED_LIVE_VERSION=V_WATCHLATER_PIP_WINDOW3; _uuid=65D18E104-D381-1D7B-4191-BB14FBF71016F05662infoc; CURRENT_QUALITY=116; buvid3=5C4356FC-CED4-B797-D0E9-0D465C57237867779infoc; b_nut=1723395567; rpdid=|(u)~Ju~J|kl0J'u~kJJml~u); LIVE_BUVID=AUTO8217257278253243; home_feed_column=5; bili_ticket=eyJhbGciOiJIUzI1NiIsImtpZCI6InMwMyIsInR5cCI6IkpXVCJ9.eyJleHAiOjE3MjY2NzExOTIsImlhdCI6MTcyNjQxMTkzMiwicGx0IjotMX0.HL4benw1AXqZyCPuhdJ0gWt_ntTJ11SaspK8rVkM4Nw; bili_ticket_expires=1726671132; SESSDATA=62b3d1f9%2C1741976682%2C01ac3%2A92CjBKLlT2PXjk2hmj_l4GXirVUtBEUJu-ii7ymQtB_b7urFREHxDukjCy1zRg6t4Fq_USVld0eW1pNGtoZ2prQWRCRUg3aTZZTzRUUE1wc1M2VkpGZDhTZzY3OHhwZ3BGTEQ4am9tOTJLMlUtZUduS2lCMjhpZS1HQU1laGRReUpoQ3VwdWdYS3FBIIEC; bili_jct=f1753715b455ce2db99ec05354cf2c00; fingerprint=262de2a503b05140a20bda05841f9755; buvid_fp=262de2a503b05140a20bda05841f9755; PVID=2; browser_resolution=2040-1026; bp_t_offset_5493983=978040246019031040; b_lsid=62D18E35_19203235E8B; sid=86fq5dr0",
+    "Referer":"https://search.bilibili.com/all?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=3"
+}
+
+def has_duplicates(lst):  #判断列表中是否有重复元素
+    return len(lst) != len(set(lst))
+
+def get_videos_cid(max_videos=300):  #获取视频BV号
+    bv_list = []
+    c_list = []
+    i = 1
+    while len(bv_list) < max_videos:
+        url = f"https://search.bilibili.com/all?vt=45910958&keyword=2024%E5%B7%B4%E9%BB%8E%E5%A5%A5%E8%BF%90%E4%BC%9A&from_source=webtop_search&spm_id_from=333.788&search_source=3&page={i}"
+
+        #为了防止被拦截，打个瞌睡
+        time.sleep(2)
+        resp = requests.get(url, headers=headers)
+        resp.encoding = "utf-8"
+
+        #错误判断
+        if resp.status_code != 200:
+            print(f"第{i}页视频请求失败，状态码: {resp.status_code}")
+        else:
+            i += 1
+            bv_id_re = r'BV\w+'
+            single_page_bv_ids = re.findall(bv_id_re, resp.text)
+            single_page_bv_ids = list(set(single_page_bv_ids))
+
+            #提取每页视频的BV号
+            for bv_ids in single_page_bv_ids:
+                if len(bv_list) >= max_videos:
+                    break
+                bv_list.append(bv_ids)
+                bv_list = list(set(bv_list))
+
+    for bv_ids in bv_list:
+        resp1 = requests.get(f"https://api.bilibili.com/x/player/pagelist?bvid={bv_ids}",headers=headers)
+        resp1.encoding = "utf-8"
+
+        if resp1.status_code == 200:
+            c_id_re = r'"cid"\s*:\s*(\d+)'
+            single_page_c_ids = re.findall(c_id_re, resp1.text)
+            single_page_c_ids = list(set(single_page_c_ids))
+
+            #提取每个BV号对应的cid（由于某些视频有分p，导致有多个cid，所以这里需要遍历）
+            for c_ids in single_page_c_ids:
+                if len(c_list) >= max_videos:
+                    break
+                c_list.append(c_ids)
+                c_list = list(set(c_list))
+
+    print(f"最终cid列表: {c_list}")
+    print(f"最终cid数量: {len(c_list)}")
+    if has_duplicates(c_list):
+        print("列表中有重复cid！")
+    else:
+        print("列表中没有重复cid！")
+    return (c_list)
+
+def get_danmu(c_list):  #通过cid获取视频弹幕
+    danmu_list = []
+
+    for c_ids in c_list:
+        url = f"https://comment.bilibili.com/{c_ids}.xml"
+        resp = requests.get(url, headers=headers)
+        resp.encoding = "utf-8"
+
+        #错误判断
+        if resp.status_code != 200:
+            print(f"cid为{c_ids}的视频获取弹幕失败，状态码: {resp.status_code}")
+        else:
+            danmu_re = r'<d[^>]*>(.*?)</d>'
+            single_video_danmus = re.findall(danmu_re, resp.text)
+            single_video_danmus = list(single_video_danmus)
+            danmu_list.extend(single_video_danmus)
+            print(f"cid为{c_ids}的视频获取弹幕成功！")
+
+    return danmu_list
+
+c_list = get_videos_cid()
+danmu_list = get_danmu(c_list)
+
+#写入文件
+with open('danmu.txt', 'w', encoding="utf-8") as f:
+    for dm in danmu_list:
+        f.write(str(dm) + "\n")