From 76835302bc4d6e4c44a48971aa0629ccd3ce4dd2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=A2=A6=E6=83=B3=E6=A9=A1=E7=9A=AE=E6=93=A6?= Date: Fri, 16 Jul 2021 17:34:32 +0800 Subject: [PATCH] =?UTF-8?q?=E5=B0=8F=E5=90=83=E5=8A=A0=E7=9B=9F=E5=BA=97?= =?UTF-8?q?=E6=95=B0=E6=8D=AE?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- ...23\345\217\226\345\255\246\344\271\240.py" | 99 +++++++++++++++++++ 1 file changed, 99 insertions(+) create mode 100644 "NO14/\345\260\217\345\220\203\345\212\240\347\233\237\345\272\227\346\225\260\346\215\256\346\212\223\345\217\226\345\255\246\344\271\240.py" diff --git "a/NO14/\345\260\217\345\220\203\345\212\240\347\233\237\345\272\227\346\225\260\346\215\256\346\212\223\345\217\226\345\255\246\344\271\240.py" "b/NO14/\345\260\217\345\220\203\345\212\240\347\233\237\345\272\227\346\225\260\346\215\256\346\212\223\345\217\226\345\255\246\344\271\240.py" new file mode 100644 index 0000000..8a96dbe --- /dev/null +++ "b/NO14/\345\260\217\345\220\203\345\212\240\347\233\237\345\272\227\346\225\260\346\215\256\346\212\223\345\217\226\345\255\246\344\271\240.py" @@ -0,0 +1,99 @@ +import requests +from lxml import etree +import time +import re +import random + +USER_AGENTS = [ + "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)", + "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)", + "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)", + "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)", + "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)", + "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)", + "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)", + "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)", + "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6", + "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1", + "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0", + "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5", + "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6", + "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11", + "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20", + "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52", +] + + +def run(url, index): + try: + headers = {"User-Agent": random.choice(USER_AGENTS)} + res = requests.get(url=url, headers=headers) + res.encoding = "utf-8" + html = res.text + with open(f"./html/{index}.html", "w+", encoding="utf-8") as f: + f.write(html) + except Exception as e: + print(e) + + +def list_str(my_list): + return ",".join(my_list) + + +def get_data(): + for i in range(1, 130): + with open(f"./html/{i}.html", "r", encoding="utf-8") as f: + html = f.read() + element = etree.HTML(html) + # contains 函数 获取包含 xxx 的元素，类似的还有 starts-with,ends-with,last + origin_li = element.xpath("//ul[contains(@class,'xm-list')]/li") + # 循环抓取 li 内部数据 + for item in origin_li: + + # 提取加盟名称 + # title = item.xpath(".//div[@class='r']/h4/text()")[0] + title = item.xpath("./div[@class='top']/a/@title")[0] + # 提取超链接 + detail_link = "http:" + item.xpath("./div[@class='top']/a/@href")[0] + + + # 提取特殊标签 + special_tag = list_str(item.xpath("./@class")) + # 当包含特殊标签 xm-list2 时，使用不同的提取规则 + + if special_tag != "xm-list2": + # 提取标签 + tags = "#".join(item.xpath(".//div[@class='bot']/span[@class='label']/text()")) + # 提取投资价格 + price = list_str(item.xpath(".//div[@class='bot']/span[@class='money']/b/text()")) + # 地址和行业 + city_industry = list_str(item.xpath("./div[@class='bot']/p/span/text()")) + + long_str = f"{title},{detail_link}, {tags}, {price}, {city_industry}" + save(long_str) + else: + # 地址和行业 + city_industry = list_str(item.xpath("./div[@class='top']/a/div/p[2]/span/text()")) + long_str = f"{title},{detail_link}, {0}, {0}, {city_industry}" + save(long_str) + + + +def save(long_str): + try: + with open(f"./jiameng.csv", "a+",encoding="utf-8") as f: + f.write("\n"+long_str) + except Exception as e: + print(e) + +if __name__ == '__main__': + + # for i in range(1, 130): + # print(f"正在爬取第{i}页数据") + # run(f"https://www.3158.cn/xiangmu/canyin/?pt=all&page={i}", i) + + get_data() + + print("全部提取完毕") + + -- GitLab