单线程版：
1 import urllib.request 2 import urllib.parse 3 import urllib.error 4 import re,time 5 headers = ("User-Agent", 6 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3107.4 Safari/537.36") 7 operner = urllib.request.build_opener() 8 operner.addheaders = [headers] 9 urllib.request.install_opener(operner) 10 11 list_url = [] 12 13 14 ###使用代理获取网页url内容 15 def use_proxy(url): 16 try: 17 # proxy = urllib.request.ProxyHandler({'http':proxy_addr}) ##使用代理版 18 # operner = urllib.request.build_opener() 19 # urllib.request.install_opener(operner) 20 headers = ("User-Agent", 21 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3107.4 Safari/537.36") 22 operner = urllib.request.build_opener() 23 operner.addheaders = [headers] 24 urllib.request.install_opener(operner) 25 data = urllib.request.urlopen(url).read().decode('utf-8') 26 # print (data) 27 return data 28 except urllib.error.URLError as e: 29 if hasattr(e, "code"): 30 print(e.code) 31 elif hasattr(e, "reason"): 32 print(e.reason) 33 34 except Exception as e: 35 print("exception" + str(e)) 36 time.sleep(1) 37 38 ##获取要爬取的url 39 def get_url(key, pagestart, pageend): 40 try: 41 42 keycode = urllib.parse.quote(key) 43 44 for page in range(pagestart, pageend + 1): 45 url = "http://weixin.sogou.com/weixin?query=%s&_sug_type_=&s_from=input&_sug_=n&type=%d&page=1&ie=utf8" % ( 46 keycode, page) 47 data1 = use_proxy(url) 48 #print("data1的内容是", data1) 49 listurl_pattern = '<h3>.*?("http://.*?)</h3>' 50 result = re.compile(listurl_pattern, re.S).findall(data1) 51 for i in range(len(result)): 52 res = result[i].replace("amp;", "").split(" ")[0].replace("\"", "") 53 list_url.append(res) 54 #print(list_url) 55 return list_url 56 except urllib.error.URLError as e: 57 if hasattr(e, "code"): 58 print(e.code) 59 elif hasattr(e, "reason"): 60 print(e.reason) 61 except Exception as e: 62 print("exception:", e) 63 64 ##通过获取的url爬行内容数据并处理 65 def get_url_content(list_url): 66 fh1=open("D:\\python-script\\1.html", 'wb') 67 html1 = '''<!DOCTYPE html>\n<html xmlns="http://www.w3.org/1999/xhmtl">\n<head>\n<meta http-equiv="Content-Type" content="text/html; charset=utf-8">\n<title>微信文章</title></head>\n<body>''' 68 fh1.write(html1.encode("utf-8")) 69 fh1.close() 70 fh = open("D:\\python-script\\1.html", 'ab') 71 for url in list_url: 72 data_content = use_proxy(url) 73 #print (data_content) 74 #sys.exit() 75 title_pattern = '<h2.*>.*?</h2>' 76 result_title = re.compile(title_pattern, re.S).findall(data_content) 77 ##标题(str) 78 res_title = result_title[0].replace("<h2 class=\"rich_media_title\" id=\"activity-name\">", "").replace("</h2>", 79 "").strip() 80 81 content_pattern = '>' 82 content = re.compile(content_pattern, re.S).findall(data_content) 83 84 try: 85 fh.write(res_title.encode("utf-8")) 86 for i in content: 87 fh.write(i.strip().encode("utf-8")) 88 except UnicodeEncodeError as e: 89 continue 90 91 fh.write("</body></html>".encode("utf-8")) 92 93 if __name__ == '__main__': 94 pagestart = 1 95 pageend = 2 96 key = "人工智能" 97 get_url(key, pagestart, pageend) 98 get_url_content(list_url)