1、一些公共方法的准备
获取数据库链接：
import pymysql # 获得数据库链接对象 def getConnect(database): DATABASE = { 'host': 'localhost', 'database': database, 'user': 'root', 'password': '123456' } return pymysql.connect(**DATABASE)
获取页面soup对象：
import requests from bs4 import BeautifulSoup #转换成soup对象 def to_soup(str): return BeautifulSoup(str,'lxml') #通过url和header获取页面soup对象 def get_soup(url,header): response=requests.get(url,headers=header) return to_soup(response.text)
2、爬取BOSS直聘python相关岗位的实现
定义工作信息对象：
class WorkInfo: def __init__(self, title, salary, site, experience, education, job_url, company,release_date,get_date): self.title = title self.salary = salary self.site = site self.experience = experience self.education = education self.job_url = job_url self.company = company self.release_date = release_date self.get_date = get_date
获取工作信息到定义的对象的集合：
# 获取工作信息集合 def getWorkInfos(url, header): # 获得页面soup对象 htmlSoup = rep.get_soup(url, header) workInfos = [] # 获取页面内容块状列表 job_infos = htmlSoup.find_all('div', class_='job-primary') if len(job_infos)==0: print('已到空白页!!!') return workInfos # 遍历每块，获取每块详细类容 print('开始爬取页面数据!') for job_info_soup in job_infos: # 标题 title = job_info_soup.find('div', class_='job-title').get_text() # 薪资 salary = job_info_soup.find('span', class_='red').get_text() infos = str(job_info_soup.find('p')) infosList = tool.toContent(infos) # 工作地址 site = infosList[0] # 工作经验 experience = infosList[1] # 学历要求 education = infosList[2] # 详细信息链接 job_url = job_info_soup.find('a').get('href') # 公司名 company = job_info_soup.find('div', class_='company-text').find('a').get_text() # 发布时间 release_date = job_info_soup.find('div', class_='info-publis').find('p').get_text()[3:] # 拼接获取符合数据库要求的日期字符串 if '昨' in release_date: release_date=time.strftime("%Y-%m-%d",time.localtime(time.time()-86400)) elif ':' in release_date: release_date=time.strftime("%Y-%m-%d") else: release_date = str(time.localtime().tm_year) + '-' + re.sub(r'[月,日]', '-', release_date)[:-1] # 获取数据的时间 get_date = time.strftime("%Y-%m-%d %H:%M:%S") workInfo = WorkInfo(title, salary, site, experience, education, job_url, company, release_date, get_date) workInfos.append(workInfo) print('爬取页面数据完毕！') return workInfos
把获取到的工作信息集合存入数据库：
# 存入数据库 def toDatabase(workInfos): print('开始存入数据库') db = database.getConnect('reptile') cursor = db.cursor() for workInfo in workInfos: sql = "INSERT INTO `work_info` (`title`, `salary`, `site`, `experience`, `education`, `job_url`, `company`, `release_date`, `get_date`)" \ " VALUES ('%s','%s','%s','%s','%s','%s','%s','%s','%s')" \ % (workInfo.title, workInfo.salary, workInfo.site, workInfo.experience, workInfo.education, workInfo.job_url, workInfo.company, workInfo.release_date,workInfo.get_date) cursor.execute(sql) cursor.close() db.commit() db.close() print('存入数据库完毕!')
爬取工作实现：
url = 'https://www.zhipin.com/c101270100/?' header = { 'user-agent': 'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36', 'referer': '', 'cookie':'lastCity=101270100; _uab_collina=155876824002955006866925; t=DPiicXvgrhx7xtms; wt=DPiicXvgrhx7xtms; sid=sem_pz_bdpc_dasou_title; __c=1559547631; __g=sem_pz_bdpc_dasou_title; __l=l=%2Fwww.zhipin.com%2F%3Fsid%3Dsem_pz_bdpc_dasou_title&r=https%3A%2F%2Fsp0.baidu.com%2F9q9JcDHa2gU2pMbgoY3K%2Fadrc.php%3Ft%3D06KL00c00fDIFkY0IWPB0KZEgsZb1OwT00000Kd7ZNC00000JqHYFm.THdBULP1doZA80K85yF9pywdpAqVuNqsusK15yF9m1DdmWfdnj0sm1PhrAf0IHYYnD7aPH9aPRckwjRLrjbsnYfYfWwaPYwDnHuDfHcdwfK95gTqFhdWpyfqn1czPjmsPjnYrausThqbpyfqnHm0uHdCIZwsT1CEQLILIz4lpA-spy38mvqVQ1q1pyfqTvNVgLKlgvFbTAPxuA71ULNxIA-YUAR0mLFW5HRvnH0s%26tpl%3Dtpl_11534_19713_15764%26l%3D1511867677%26attach%3Dlocation%253D%2526linkName%253D%2525E6%2525A0%252587%2525E5%252587%252586%2525E5%2525A4%2525B4%2525E9%252583%2525A8-%2525E6%2525A0%252587%2525E9%2525A2%252598-%2525E4%2525B8%2525BB%2525E6%2525A0%252587%2525E9%2525A2%252598%2526linkText%253DBoss%2525E7%25259B%2525B4%2525E8%252581%252598%2525E2%252580%252594%2525E2%252580%252594%2525E6%252589%2525BE%2525E5%2525B7%2525A5%2525E4%2525BD%25259C%2525EF%2525BC%25258C%2525E6%252588%252591%2525E8%2525A6%252581%2525E8%2525B7%25259F%2525E8%252580%252581%2525E6%25259D%2525BF%2525E8%2525B0%252588%2525EF%2525BC%252581%2526xp%253Did(%252522m3224604348_canvas%252522)%25252FDIV%25255B1%25255D%25252FDIV%25255B1%25255D%25252FDIV%25255B1%25255D%25252FDIV%25255B1%25255D%25252FDIV%25255B1%25255D%25252FH2%25255B1%25255D%25252FA%25255B1%25255D%2526linkType%253D%2526checksum%253D8%26wd%3Dboss%25E7%259B%25B4%25E8%2581%2598%26issp%3D1%26f%3D3%26ie%3Dutf-8%26rqlang%3Dcn%26tn%3Dbaiduhome_pg%26oq%3D%2525E5%25258D%25259A%2525E5%2525AE%2525A2%2525E5%25259B%2525AD%26inputT%3D9649%26prefixsug%3Dboss%26rsp%3D0&g=%2Fwww.zhipin.com%2F%3Fsid%3Dsem_pz_bdpc_dasou_title; Hm_lvt_194df3105ad7148dcf2b98a91b5e727a=1558768262,1558768331,1559458549,1559547631; JSESSIONID=A0FC9E1FD0F10E42EAB681A51AC459C7;' ' __a=86180698.1558768240.1559458549.1559547631.63.3.6.6; Hm_lpvt_194df3105ad7148dcf2b98a91b5e727a=1559551561' 'referer: https://www.zhipin.com/c101270100/?query=python&page=2&ka=page-2' } query='python' page=1 while True: print("开始第：{} 页".format(page)) purl=url+'query='+query+'&page='+str(page)+'&ka=page-'+str(page) workInfos = getWorkInfos(purl, header) if len(workInfos)==0: print('结束爬取!') break toDatabase(workInfos) page=page+1
3、涉及的小知识
自制去取html标签，把标签内夹杂的内容存入list中：
# 通过正则表达式去掉HTML标签，获取标签内的文字内容列表 def toContent(str): infos=re.split('<[^>]*>', str) # 去除空元素 return list(filter(None,infos))
时间的相关操作
用‘-’替换‘月’‘日’：
re.sub(r'[月,日]', '-', release_date)
获取前一天’：
release_date=time.strftime("%Y-%m-%d",time.localtime(time.time()-86400))