代码之前爬都是正确的,为什么现在爬不了了??
mid = re.findall('bilibili\.com/(\d+)',html_url)[0]
info_url = "https://api.bilibili.com/x/space/wbi/arc/search?mid={}".format(mid)
print(info_url)
response = self.get_response(info_url)
json_data = json.loads(response.text)
if 'code' in json_data:
if json_data['code'] == -403:
self.process.emit("解析异常")
self.quit()
return
print(119, json_data['code'])
# video_info列表
video_info_list = []
total = len(json_data['data']['list']['vlist'])
author_name = json_data['data']['list']['vlist'][0]['author']
for i, item in enumerate(json_data['data']['list']['vlist']):
if self.stop:
break
bvid = item['bvid']
item_title = item['title']
item_title = re.sub(r'[\/:*?"<>|\s]', '', item_title) # 去除双引号
# item_title = re.sub(r'[^\u4e00-\u9fa5]+', '', item_title) # 去除双引号
item_url = "https://www.bilibili.com/video/" + str(bvid)
item_video_info = [item_title, item_url, bvid]
video_info_list.append([])
video_info_list[i] = item_video_info
print(video_info_list[i])
---后续
应该就是爬多了被封了,我用的VMware虚拟机爬就解决了~