Python爬蟲教程：爬取下載b站影片【附源碼】
- 2020 年 3 月 31 日
- 筆記
下載倉庫
[email protected]:inspurer/PythonSpider.git
或者直接下載:https://github.com/inspurer/PythonSpider/tree/master/bilibili
替換
隨便打開一個b站的介面，比如
將url複製到程式碼中去，運行程式碼，稍等一會兒，上述圖中的影片就被下載下來了。
完整程式碼奉上！
import requests import re import json from contextlib import closing from pyquery import PyQuery as pq from requests import RequestException class bilibili(): def __init__(self): self.getHtmlHeaders={ 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8', 'Accept-Encoding': 'gzip, deflate, br', 'Accept-Language': 'zh-CN,zh;q = 0.9' } self.downloadVideoHeaders={ 'Origin': 'https://www.bilibili.com', 'Referer': 'https://www.bilibili.com/video/av26522634', 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36', } #一般這裡得到的網頁源碼和F12查看看到的不一樣，因為F12開發者工具里的源碼經過了瀏覽器的解釋 def getHtml(self,url): try: response = requests.get(url=url, headers= self.getHtmlHeaders) print(response.status_code) if response.status_code == 200: return response.text except RequestException: print('請求Html錯誤:') def parseHtml(self,html): #用pq解析得到影片標題 doc = pq(html) video_title = doc('#viewbox_report > h1 > span').text() #用正則、json得到影片url;用pq失敗後的無奈之舉 pattern = r'<script>window.__playinfo__=(.*?)</script>' result = re.findall(pattern, html)[0] temp = json.loads(result) #temp['durl']是一個列表，裡面有很多字典 #video_url = temp['durl'] for item in temp['durl']: if 'url' in item.keys(): video_url = item['url'] #print(video_url) return{ 'title': video_title, 'url': video_url } def download_video(self,video): title = re.sub(r'[/:*?"<>|]', '-', video['title']) # 去掉創建文件時的非法字元 url = video['url'] filename = title +'.flv' with open(filename, "wb") as f: f.write(requests.get(url=url, headers=self.downloadVideoHeaders, stream=True, verify=False).content) #closing適用於提供了 close() 實現的對象，比如網路連接、資料庫連接 # with closing(requests.get(video['url'], headers=self.downloadVideoHeaders, stream=True, verify=False)) as res: # if res.status_code == 200: # with open(filename, "wb") as f: # for chunk in res.iter_content(chunk_size=1024): # if chunk: # f.write(chunk) def run(self,url): self.download_video(self.parseHtml(self.getHtml(url))) if __name__ == '__main__': url = 'https://www.bilibili.com/video/av18100312' bilibili().run(url)
運行結果奉上！
