import requests from lxml import etree headers = {'User-Agen':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.4098.3 Safari/537.36'} video_list = [] for i in range(4,19): url = 'http://www.d9dyy.com/html/dl/list_%s.html'%i page_text = requests.get(url=url,headers=headers).text tree = etree.HTML(page_text) page_li = tree.xpath('/html/body/div[2]/div[2]/ul/li') for li in page_li: li_url = li.xpath('./a/@href')[0] # print(li_url) real_url = 'www.d9dyy.com'+li_url video_list.append(real_url) for video_li in video_list: video_li = 'http://'+video_li video_text = requests.get(url=video_li,headers=headers).text video_tree = etree.HTML(video_text) video_player_url = video_tree.xpath('/html/body/div[2]/div[1]/div[1]/iframe/@src')[0] # print(video_player_url) fp = open('网站影片播放链接.txt','w',encoding='UTF-8') fp.write(video_player_url) print('辛辛苦苦')
中间有点小不足,太懒了,没把名字给写上去。爬虫慢慢娴熟了,后面要学习更精湛的技术了,就是反反反。。。爬虫技术。哈哈哈