学会使用正则表达式
1. 用正则表达式判定邮箱是否输入正确。
import redef validateEmail(email): if len(email) > 7: if re.match("^.+\\@(\\[?)[a-zA-Z0-9\\-\\.]+\\.([a-zA-Z]{2,3}|[0-9]{1,3})(\\]?)$", email) != None: print('good') # return 1 # return 0 print('exit')validateEmail('18814328327@163.com')
2. 用正则表达式识别出全部电话号码。
# -*- coding: utf-8 -*-from __future__ import print_function, divisionimport res = 'ID: 042 SEX: M DOB: 1967-08-17 Status: Active 1968 NUM:18814328327'p = re.compile(r'(?:)\d{11}')all_items = re.findall(p,s)map(print, all_items)print(all_items)
import restr = '''版权所有:广州商学院 地址:广州市黄埔区九龙大道206号 学校办公室:020-82876130 招生电话:020-82872773 粤公网安备 44011602000060号 粤ICP备15103669号'''print(re.findall('(\d{3,4})-(\d{6,8})',str))
3. 用正则表达式进行英文分词。re.split('',news)
import restring = "Had I not seen the Sun,I could have borne the shade."print(re.split('[\s,.?\-]+',string))
4. 使用正则表达式取得新闻编号
import renewUrl = "http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html"newsId = re.findall("\_(.*).html",newUrl)[0].split("/")[-1];print(newsId)
5. 生成点击次数的Request URL
import renewUrl = "http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html"newsId = re.findall("\_(.*).html",newUrl)[0].split("/")[-1];RequestUrl = "http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80".format(newsId)print(RequestUrl)
6. 获取点击次数
import renewUrl = "http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html"newsId = re.findall("\_(.*).html",newUrl)[0].split("/")[-1];res = requests.get("http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80".format(newsId))print(int(res.text.split(".html")[-1].lstrip("('").rsplit("');")[0]))
7. 将456步骤定义成一个函数 def getClickCount(newsUrl):
import redef getClickCount(newsUrl): newsId = re.findall("\_(.*).html",newUrl)[0].split("/")[-1]; res = requests.get("http://oa.gzcc.cn/api.php?op=count&id= {}&modelid=80".format(newsId)) return int(res.text.split(".html")[-1].lstrip("('").rsplit("');")[0])
8. 将获取新闻详情的代码定义成一个函数 def getNewDetail(newsUrl):
def getNewDetail(newsUrl): detail_res = requests.get(newsUrl) detail_res.encoding = "utf-8" detail_soup = BeautifulSoup(detail_res.text, "html.parser") print(detail_soup.select("#content")[0].text) # 正文 print(time, title, description, newsUrl) content = detail_soup.select("#content")[0].text info = detail_soup.select(".show-info")[0].text date_time = info.lstrip('发布时间:')[:19] print(info)
9. 取出一个新闻列表页的全部新闻 包装成函数def getListPage(pageUrl):
def getlist(url): for news in soup.select("li"): if len(news.select(".news-list-title"))>0: #排除为空的li time = news.select(".news-list-info")[0].contents[0].text title = news.select(".news-list-title")[0].text description = news.select(".news-list-description")[0].text detail_url = news.select('a')[0].attrs['href'] print(time, title, description, detail_url)
10. 获取总的新闻篇数,算出新闻总页数包装成函数def getPageN():
def getPageN(url): res = requests.get(url) res.encoding = 'utf-8' soup = BeautifulSoup(res.text, 'html.parser') return int(soup.select(".a1")[0].text.rstrip("条"))//10+1
11. 获取全部新闻列表页的全部新闻详情。
def getall(url): for num in range(2,getPageN(url)): listpageurl="http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html".format(num) getlist(listpageurl) getNewDetail(listpageurl)