# encoding:utf-8import requestsimport reimport json def parse_page(url): # 1.请求网站 headers = { "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.62 Safari/537.36" } response = requests.get(url, headers=headers) text = response.text # 2.解析网站 titles = re.findall(r'<div\sclass="cont">.*?<b>(.*?)</b>', text, re.DOTALL) # print json.dumps(titles, encoding="utf-8", ensure_ascii=False) times = re.findall(r'<p\sclass="source">.*?<a\s.*?>(.*?)</a>', text, re.DOTALL) # print json.dumps(times, encoding="utf-8", ensure_ascii=False) authors = re.findall(r'<p class="source">.*?<a.*?<a.*?>(.*?)</a>', text, re.DOTALL) poems_ret = re.findall(r'<div class="contson" id=.*?>(.*?)</div>', text, re.DOTALL) poems = [] for poem in poems_ret: temp = re.sub("<.*?>", "", poem) poems.append(temp.strip()) # for index, value in enumerate(titles): # print titles[index] # print times[index] # print authors[index] # print poems[index] # print "*"*50 # zip函数自动实现上述组合 results = [] for value in zip(titles, times, authors, poems): title, time, author, poem = value result = { "标题": title, "朝代": time, "作者": author, "原文": poem } print result["标题"] results.append(result) # print results def main(): url_base = "https://www.xzslx.net/gushi/" for i in range(1, 11): url = url_base.format(i) print " "*20+"优美古诗文"+" "*20 print "*"*50 parse_page(url) print "*"*50 if __name__ == '__main__': main()2. 输出来的结果是：
C:\DDD\python22\python.exe C:/PyCharm/dytt_spider/poems.py 古诗文 **************************************************关山月明月出天山，苍茫云海间。长风几×××，吹度玉门关。 汉下白登道，胡窥青海湾。[2] 由来征战地，不见有人还。戍客望边邑，思归多苦颜。 高楼当此夜，叹息未应闲。************************************************** 古诗文 **************************************************陇西行四首·其二誓扫匈奴不顾身，五千貂锦丧胡尘。可怜无定河边骨，犹是春闺梦里人！************************************************** 古诗文 **************************************************嫦娥（嫦娥应悔偷灵药)云母屏风烛影深， 长河渐落晓星沉。 嫦娥应悔偷灵药， 碧海青天夜夜心。**************************************************
Process finished with exit code 0
古诗文网站的网络爬虫编写方式，通过网络爬虫抓去内容
原文地址：http://blog.51cto.com/3214135/2156136