Python爬虫之爬取动漫之家 小白上手爬虫第一天，简单爬取网站动漫之家。 小小目标： 1.爬取5页的动漫； 2.以list返回其动漫地址和动漫名字； 简单粗暴，直接附上源码：
import requests import re # 获取页面 def getHTMLText(url): try: kv = { 'cookie': 'thw=cn; v=0; t=ab66dffdedcb481f77fd563809639584; cookie2=1f14e41c704ef58f8b66ff509d0d122e; _tb_token_=5e6bed8635536; cna=fGOnFZvieDECAXWIVi96eKju; unb=1864721683; sg=%E4%B8%8B3f; _l_g_=Ug%3D%3D; skt=83871ef3b7a49a0f; cookie1=BqeGegkL%2BLUif2jpoUcc6t6Ogy0RFtJuYXR4VHB7W0A%3D; csg=3f233d33; uc3=vt3=F8dBy3%2F50cpZbAursCI%3D&id2=UondEBnuqeCnfA%3D%3D&nk2=u%2F5wdRaOPk21wDx%2F&lg2=VFC%2FuZ9ayeYq2g%3D%3D; existShop=MTU2MjUyMzkyMw%3D%3D; tracknick=%5Cu4E36%5Cu541B%5Cu4E34%5Cu4E3F%5Cu5929%5Cu4E0B; lgc=%5Cu4E36%5Cu541B%5Cu4E34%5Cu4E3F%5Cu5929%5Cu4E0B; _cc_=WqG3DMC9EA%3D%3D; dnk=%5Cu4E36%5Cu541B%5Cu4E34%5Cu4E3F%5Cu5929%5Cu4E0B; _nk_=%5Cu4E36%5Cu541B%5Cu4E34%5Cu4E3F%5Cu5929%5Cu4E0B; cookie17=UondEBnuqeCnfA%3D%3D; tg=0; enc=2GbbFv3joWCJmxVZNFLPuxUUDA7QTpES2D5NF0D6T1EIvSUqKbx15CNrsn7nR9g%2Fz8gPUYbZEI95bhHG8M9pwA%3D%3D; hng=CN%7Czh-CN%7CCNY%7C156; mt=ci=32_1; alitrackid=www.taobao.com; lastalitrackid=www.taobao.com; swfstore=97213; x=e%3D1%26p%3D*%26s%3D0%26c%3D0%26f%3D0%26g%3D0%26t%3D0%26__ll%3D-1%26_ato%3D0; uc1=cookie16=UtASsssmPlP%2Ff1IHDsDaPRu%2BPw%3D%3D&cookie21=UIHiLt3xThH8t7YQouiW&cookie15=URm48syIIVrSKA%3D%3D&existShop=false&pas=0&cookie14=UoTaGqj%2FcX1yKw%3D%3D&tag=8&lng=zh_CN; JSESSIONID=A502D8EDDCE7B58F15F170380A767027; isg=BMnJJFqj8FrUHowu4yKyNXcd2PXjvpa98f4aQWs-RbDvsunEs2bNGLfj8BYE6lWA; l=cBTDZx2mqxnxDRr0BOCanurza77OSIRYYuPzaNbMi_5dd6T114_OkmrjfF96VjWdO2LB4G2npwJ9-etkZ1QoqpJRWkvP.; whl=-1%260%260%261562528831082', 'user-agent': 'Mozilla/5.0' } r = requests.get(url,timeout = 30,headers=kv) r.raise_for_status() r.encoding = r.apparent_encoding return r.text except: return "获取页面失败" # 解析页面 def parsePage(ilt,html): try: # 匹配 res = re.compile(r'<a target="_blank" href="(.*?)">(.*?)</a>',re.S) web = re.findall(res,html) for i in range(len(web)): ilt.append([web[i][0],web[i][1]]) return ilt except: print("解析页面失败") def printCommediesList(ilt): for g in range(len(ilt)): print(ilt[g]) def main(): cate = "3262" # 少年漫画的代码 # 设置爬取深度为3 depth = 5 start_url = "https://www.dmzj.com/category/0-0-"+"3262"+"-0-0-0-" infoList = [] count = 0 for i in range(1,(depth+1)): count += 1 try: print(count) url = start_url + str(i) + ".html" #url = "https://www.dmzj.com/category/0-0-"+"3262"+"-0-0-0-1.html" html = getHTMLText(url) infoList = parsePage(infoList,html) print(printCommediesList(infoList)) print("\r爬取页面当前进度: {:.2f}%".format(count * 100 / depth), end="") # 显示进度条 except: return "unsucceeded" if __name__ == '__main__': main()