爬虫目的:爬取拉勾网上数据分析岗的数据,以便分析当前数据分析岗的需求现状。
爬虫实现的功能:根据城市名称、岗位名称关键字,即可爬取拉勾网上所需的数据信息。
爬虫的主要模块:
主函数与信息存储模块main.py
网页下载模块https.py
网页解析模块parse.py
IP代理池setting.py
# main.py‘‘‘ 拉钩网对于同一ip的大量请求行为肯定会进行封禁,所以需要准备代理池。 为了实现高自动化,需要对一系列可能出现的异常情况进行处理,断点处理,确保程序不挂。 为了提高效率,加入多线程。 数据持久化,在持久化之前需要先进行清洗。 ‘‘‘ import https,parse,setting # import https.Http , parse.Parse , setting.headers ,setting.cookies import time import logging import codecs logging.basicConfig(level=logging.ERROR, format=‘%(asctime)s Process%(process)d:%(thread)d %(message)s‘, datefmt=‘%Y-%m-%d %H:%M:%S‘, filename=‘diary.log‘, filemode=‘a‘) def process(value): # 处理字符串保存为csv文件时,因双引号、逗号引起的分隔问题。 if ("\"" in value): # 若发现有双引号,将双引号替换为单引号。 value = value.replace("\"", "\‘") # value = value.replaceAll("\"", "\"\"") # value = "\"" + value + "\"" if ("," in value or "," in value): # 若发现有逗号 需给整体前后加双引号 value = "\"" + value + "\"" return value def getInfo(url, para): """ 获取信息 """ generalHttp = https.Http() htmlCode = generalHttp.post(url, para=para, headers=setting.headers, cookies=setting.cookies) generalParse = parse.Parse(htmlCode) pageCount = generalParse.parsePage() info = [] for i in range(1, pageCount + 1): print(‘第%s页‘ % i) para[‘pn‘] = str(i) htmlCode = generalHttp.post(url, para=para, headers=setting.headers, cookies=setting.cookies) generalParse = parse.Parse(htmlCode) info = info + getInfoDetail(generalParse) time.sleep(2) return info def getInfoDetail(generalParse): """ 信息解析 """ info = generalParse.parseInfo() return info def processInfo(info, para): """ 信息存储 """ logging.error(‘Process start‘) try: title = ‘companyName,positionType,positionName,companyStage,companySize,Education,WorkYear,Salary,‘ ‘district,latitude,longitude,companyType,positionLables,positionAdvantage,companyLabel\n‘ # "gbk"下csv文件不能对\t换单元格,只能换为“,” file = codecs.open(‘%s%s职位.csv‘ %(para[‘city‘],para[‘kd‘]), ‘w‘, ‘gbk‘) # encoding = ‘utf-8‘时出现乱码。故改为"gbk",或使用‘utf-8’将文件在notepad++打开转回格式‘utf-8’后再打开。 file.write(title) for p in info: line = str(p[‘companyName‘]) + ‘,‘ + str(p[‘positionType‘]) + ‘,‘ + str(p[‘positionName‘]) + ‘,‘ + str(p[‘companyStage‘]) + ‘,‘ + str(p[‘companySize‘]) + ‘,‘ +str(p[‘positionEducation‘]) + ‘,‘ + str(p[‘positionWorkYear‘]) + ‘,‘ + str(p[‘positionSalary‘]) + ‘,‘ +str(p[‘district‘]) + ‘,‘ + str(p[‘latitude‘])+ ‘,‘ +str(p[‘longitude‘])+ ‘,‘ + str(p[‘companyType‘]) + ‘,‘ + process(str(p[‘positionLables‘]))+ ‘,‘ + process(str(p[‘positionAdvantage‘]))+ ‘,‘ + process(str(p[‘companyLabel‘])) +‘\n‘ # "gbk"下csv文件不能对\t换单元格,只能换为“,” file.write(line) file.close() return True except Exception as e: print(e) return None def main(url, para): """ 主函数逻辑 """ logging.error(‘Main start‘) # 日志生成 if url: info = getInfo(url, para) # 获取信息 flag = processInfo(info, para) # 信息储存 return flag else: return None if __name__ == ‘__main__‘: kdList = [u‘数据分析‘] # keyword即搜索关键字 cityList = [u‘上海‘] url = ‘https://www.lagou.com/jobs/positionAjax.json‘ # 如何确定的? for keyword in kdList: for city in cityList: print(‘爬取%s‘ % city) para = {‘first‘: ‘true‘, ‘pn‘: ‘1‘, ‘kd‘: keyword, ‘city‘: city} flag = main(url, para) if flag: print(‘%s爬取成功‘ % city) else: print(‘%s爬取失败‘ % city)
# https.py import setting import requests, random import logging logging.basicConfig(level=logging.ERROR, format=‘%(asctime)s Process%(process)d:%(thread)d %(message)s‘, datefmt=‘%Y-%m-%d %H:%M:%S‘, filename=‘diary.log‘, filemode=‘a‘) class Http: ‘‘‘ http请求相关的操作 ‘‘‘ def __init__(self): pass def get(self, url, headers=None, cookies=None, proxy=None, timeOut=5, timeOutRetry=5): ‘‘‘ 获取网页源码 url: 网页链接 headers: headers cookies: cookies proxy: 代理 timeOut: 请求超时时间 timeOutRetry: 超时重试次数 return: 源码 ‘‘‘ if not url: logging.error(‘GetError url not exit‘) return ‘None‘ logging.error(‘Get %s‘ % url) try: if not headers: headers = {‘User-Agent‘: setting.UA[random.randint(0, len(setting.UA) - 1)]} # if not proxy: proxy = {‘http‘:"http://"+IP[random.randint(0, len(IP)-1)]} response = requests.get(url, headers=headers, cookies=cookies, proxies=proxy, timeout=timeOut) if response.status_code == 200 or response.status_code == 302: htmlCode = response.text else: htmlCode = ‘None‘ logging.error(‘Get %s %s‘ % (str(response.status_code), url)) except Exception as e: logging.error(‘GetExcept %s‘ % str(e)) if timeOutRetry > 0: htmlCode = self.get(url=url, timeOutRetry=(timeOutRetry - 1)) else: logging.error(‘GetTimeOut %s‘ % url) htmlCode = ‘None‘ return htmlCode def post(self, url, para, headers=None, cookies=None, proxy=None, timeOut=5, timeOutRetry=5): ‘‘‘ post获取响应 url: 目标链接 para: 参数 headers: headers cookies: cookies proxy: 代理 timeOut: 请求超时时间 timeOutRetry: 超时重试次数 return: 响应 ‘‘‘ if not url or not para: logging.error(‘PostError url or para not exit‘) return None logging.error(‘Post %s‘ % url) try: if not headers: headers = {‘User-Agent‘: ‘Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070309 Firefox/2.0.0.3‘} response = requests.post(url, data=para, headers=headers, cookies=cookies, proxies=proxy, timeout=timeOut) if response.status_code == 200 or response.status_code == 302: htmlCode = response.text else: htmlCode = None logging.error(‘Post %s %s‘ % (str(response.status_code), url)) except Exception as e: logging.error(‘PostExcept %s‘ % str(e)) if timeOutRetry > 0: htmlCode = self.post(url=url, para=para, timeOutRetry=(timeOutRetry - 1)) else: logging.error(‘PostTimeOut %s‘ % url) htmlCode = None return htmlCode def confirm(self, htmlCode, url, headers, cookies, proxy, catch_retry=5): ‘‘‘ 反爬,验证页面 htmlCode:网页源码 return:网页源码 ‘‘‘ # 获取网页title判断是否被ban return htmlCode def urlprocess(self, items): # + URL 中+号表示空格 %2B # 空格 URL中的空格可以用+号或者编码 %20 # / 分隔目录和子目录 %2F # ? 分隔实际的URL和参数 %3F # % 指定特殊字符 %25 # # 表示书签 %23 # & URL 中指定的参数间的分隔符 %26 # = URL 中指定参数的值 %3D content = items.replace(‘/‘, ‘%2F‘).replace(‘=‘, ‘%3D‘).replace(‘+‘, ‘%2B‘).replace( ‘ ‘, ‘%20‘).replace(‘/‘, ‘%2F‘).replace(‘?‘, ‘%3F‘).replace(‘=‘, ‘%3D‘) return content
# parse.py import re import demjson class Parse: ‘‘‘ 解析网页信息 ‘‘‘ def __init__(self, htmlCode): self.htmlCode = htmlCode self.json = demjson.decode(htmlCode) pass def parseTool(self, content): ‘‘‘ 清除html标签 ‘‘‘ if type(content) != str: return content sublist = [‘<p.*?>‘, ‘</p.*?>‘, ‘<b.*?>‘, ‘</b.*?>‘, ‘<div.*?>‘, ‘</div.*?>‘, ‘</br>‘, ‘<br />‘, ‘<ul>‘, ‘</ul>‘, ‘<li>‘, ‘</li>‘, ‘<strong>‘, ‘</strong>‘, ‘<table.*?>‘, ‘<tr.*?>‘, ‘</tr>‘, ‘<td.*?>‘, ‘</td>‘, ‘\r‘, ‘\n‘, ‘&.*?;‘, ‘&‘, ‘#.*?;‘, ‘<em>‘, ‘</em>‘] try: for substring in [re.compile(string, re.S) for string in sublist]: content = re.sub(substring, "", content).strip() except: raise Exception(‘Error ‘ + str(substring.pattern)) return content def parsePage(self): ‘‘‘ 解析并计算页面数量 return: 页面数量 ‘‘‘ totalCount = self.json[‘content‘][‘positionResult‘][‘totalCount‘] # 职位总数量 resultSize = self.json[‘content‘][‘positionResult‘][‘resultSize‘] # 每一页显示的数量 pageCount = int(totalCount) // int(resultSize) + 1 # 页面数量 return pageCount def parseInfo(self): ‘‘‘ 解析信息 ‘‘‘ info = [] for position in self.json[‘content‘][‘positionResult‘][‘result‘]: i = {} i[‘companyName‘] = position[‘companyFullName‘] i[‘positionType‘] = position[‘firstType‘] i[‘positionName‘] = position[‘positionName‘] i[‘companyStage‘] = position[‘financeStage‘] i[‘companySize‘] = position[‘companySize‘] i[‘positionEducation‘] = position[‘education‘] i[‘positionWorkYear‘] = position[‘workYear‘] i[‘positionSalary‘] = position[‘salary‘] i[‘district‘] = position[‘district‘] i[‘latitude‘] = position[‘latitude‘] i[‘longitude‘] = position[‘longitude‘] i[‘companyType‘] = position[‘industryField‘] i[‘positionLables‘] = position[‘positionLables‘] i[‘companyLabel‘] = position[‘companyLabelList‘] i[‘positionAdvantage‘] = position[‘positionAdvantage‘] info.append(i) return info
# setting.py headers = { ‘Host‘: ‘www.lagou.com‘, ‘Connection‘: ‘keep-alive‘, ‘Content-Length‘: ‘23‘, ‘Origin‘: ‘https://www.lagou.com‘, ‘X-Anit-Forge-Code‘: ‘0‘, ‘User-Agent‘: ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36‘, ‘Content-Type‘: ‘application/x-www-form-urlencoded; charset=UTF-8‘, ‘Accept‘: ‘application/json, text/javascript, */*; q=0.01‘, ‘X-Requested-With‘: ‘XMLHttpRequest‘, ‘X-Anit-Forge-Token‘: ‘None‘, ‘Referer‘: ‘https://www.lagou.com/jobs/list_java?city=%E5%B9%BF%E5%B7%9E&cl=false&fromSearch=true&labelWords=&suginput=‘, ‘Accept-Encoding‘: ‘gzip, deflate, br‘, ‘Accept-Language‘: ‘en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7‘ } # cookies cookies = { ‘user_trace_token‘: ‘20171011085044-36afc724-ae1e-11e7-947d-5254005c3644‘, ‘LGUID‘: ‘20171011085044-36afc9e6-ae1e-11e7-947d-5254005c3644‘, ‘_ga‘: ‘GA1.2.1411877279.1507683044‘, ‘index_location_city‘: ‘%E5%B9%BF%E5%B7%9E‘, ‘JSESSIONID‘: ‘ABAAABAAADEAAFI2466B2149D4B3E406932CAEA37FDF471‘, ‘_gid‘: ‘GA1.2.1604143331.1517585155‘, ‘Hm_lvt_4233e74dff0ae5bd0a3d81c6ccf756e6‘: ‘1515000882,1515252738,1516984463,1517585156‘, ‘LGSID‘: ‘20180202232556-5ce93c91-082d-11e8-abfa-5254005c3644‘, ‘PRE_UTM‘: ‘‘, ‘PRE_HOST‘: ‘‘, ‘PRE_SITE‘: ‘‘, ‘PRE_LAND‘: ‘https%3A%2F%2Fwww.lagou.com%2F‘, ‘TG-TRACK-CODE‘: ‘index_navigation‘, ‘Hm_lpvt_4233e74dff0ae5bd0a3d81c6ccf756e6‘: ‘1517585322‘, ‘LGRID‘: ‘20180202232842-c0095589-082d-11e8-abfa-5254005c3644‘, ‘SEARCH_ID‘: ‘0a887843a48a49c7bb6dae915dabdcc1‘ } # IP池 # 0(pay) or 1(free) or 2(None) TAGIP = 0 # IP IP = [] # UA UA = [‘Mozilla/5.0 (Windows NT 5.1) AppleWebKit/534.55.3 (KHTML, like Gecko) Version/5.1.5 Safari/534.55.3‘, ‘Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; TencentTraveler 4.0; Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1))‘, ‘Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1) ; Maxthon/3.0)‘, ‘Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1) ; QIHU 360EE)‘, ‘Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1) ; 360SE)‘, ‘Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; 360SE)‘, ‘Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.12) Gecko/20080219 Firefox/2.0.0.12 Navigator/9.0.0.6‘, ‘Mozilla/5.0 (Windows; U; Windows NT 5.2) AppleWebKit/525.13 (KHTML, like Gecko) Chrome/0.2.149.27 Safari/525.13‘, ‘Mozilla/5.0 (Windows; U; Windows NT 5.2) AppleWebKit/525.13 (KHTML, like Gecko) Version/3.1 Safari/525.13‘, ‘Opera/8.0 (Macintosh; PPC Mac OS X; U; en)‘, ‘Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070309 Firefox/2.0.0.3‘, ‘Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)‘, ‘Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1‘, ‘Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)‘, ‘Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)‘, ‘Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)‘, ‘Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)‘, ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11‘, ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1‘, ‘Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)‘, ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11‘, ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER‘, ‘Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER) ‘, ‘Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)‘, ‘Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)‘, ‘Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E) ‘, ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1‘, ‘Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 SE 2.X MetaSr 1.0‘, ‘Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:16.0) Gecko/20121026 Firefox/16.0‘, ‘Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5‘, ‘Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre‘, ‘Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11‘, ‘Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0)‘]
原文地址:https://www.cnblogs.com/yimengtianya1/p/9260512.html
时间: 2024-10-21 13:04:09