Python常用爬虫代码总结方便查询

Python  /  管理员 发布于 7年前   174

beautifulsoup解析页面

from bs4 import BeautifulSoupsoup = BeautifulSoup(htmltxt, "lxml")# 三种装载器soup = BeautifulSoup("<a></p>", "html.parser")### 只有起始标签的会自动补全，只有结束标签的会自动忽略### 结果为：<a></a>soup = BeautifulSoup("<a></p>", "lxml")### 结果为：<html><body><a></a></body></html>soup = BeautifulSoup("<a></p>", "html5lib")### html5lib则出现一般的标签都会自动补全### 结果为：<html><head></head><body><a><p></p></a></body></html># 根据标签名、id、class、属性等查找标签### 根据class、id、以及属性alog-action的值和标签类别查询soup.find("a",class_="title",id="t1",attrs={"alog-action": "qb-ask-uname"}))### 查询标签内某属性的值pubtime = soup.find("meta",attrs={"itemprop":"datePublished"}).attrs['content']### 获取所有class为title的标签for i in soup.find_all(class_="title"):  print(i.get_text())### 获取特定数量的class为title的标签for i in soup.find_all(class_="title",limit = 2):  print(i.get_text())### 获取文本内容时可以指定不同标签之间的分隔符，也可以选择是否去掉前后的空白。soup = BeautifulSoup('<p class="title" id="p1"><b> The Dormouses story </b></p><p class="title" id="p1"><b>The Dormouses story</b></p>', "html5lib")soup.find(class_="title").get_text("|", strip=True)#结果为：The Dormouses story|The Dormouses story### 获取class为title的p标签的idsoup.find(class_="title").get("id")### 对class名称正则：soup.find_all(class_=re.compile("tit"))### recursive参数，recursive=False时，只find当前标签的第一级子标签的数据soup = BeautifulSoup('<html><head><title>abc','lxml')soup.html.find_all("title", recursive=False)

unicode编码转中文

content = "\u65f6\u75c7\u5b85"content = content.encode("utf8","ignore").decode('unicode_escape')

url encode的解码与解码

from urllib import parse# 编码x = "中国你好"y = parse.quote(x)print(y)# 解码x = parse.unquote(y)print(x)

html转义字符的解码

from html.parser import HTMLParserhtmls = "<div><p>"txt = HTMLParser().unescape(htmls)print(txt)  . # 输出<div><p>

base64的编码与解码

import base64# 编码content = "测试转码文本123"contents_base64 = base64.b64encode(content.encode('utf-8','ignore')).decode("utf-8")# 解码contents = base64.b64decode(contents_base64)

过滤emoji表情

 def filter_emoji(desstr,restr=''):    try:      co = re.compile(u'[\U00010000-\U0010ffff]')    except re.error:      co = re.compile(u'[\uD800-\uDBFF][\uDC00-\uDFFF]')    return co.sub(restr, desstr)

完全过滤script和style标签

import requestsfrom bs4 import BeautifulSoupsoup = BeautifulSoup(htmls, "lxml")for script in soup(["script", "style"]):    script.extract()print(soup)

过滤html的标签，但保留标签里的内容

import rehtmls = "<p>abc</p>"dr = re.compile(r'<[^>]+>',re.S)htmls2 = dr.sub('',htmls)print(htmls2)  #abc正则提取内容（一般处理json）rollback({ "response": { "code": "0", "msg": "Success", "dext": "" }, "data": { "count": 3, "page": 1, "article_info": [{  "title": "“小库里”：适应比赛是首要任务 投篮终会找到节奏",  "url": "http:\/\/sports.qq.com\/a\/20180704\/035378.htm",  "time": "2018-07-04 16:58:36",  "column": "NBA",  "img": "",  "desc": "" }, {  "title": "首钢体育助力国家冰球集训队 中国冰球联赛年底启动",  "url": "http:\/\/sports.qq.com\/a\/20180704\/034698.htm",  "time": "2018-07-04 16:34:44",  "column": "综合体育",  "img": "",  "desc": "" }...] }})import re# 提取这个json中的每条新闻的title、url# (.*?)为要提取的内容，可以在正则字符串中加入.*？表示中间省略若干字符reg_str = r'"title":"(.*?)",.*?"url":"(.*?)"'pattern = re.compile(reg_str,re.DOTALL)items = re.findall(pattern,htmls)for i in items:  tilte = i[0]  url = i[1]

时间操作

# 获取当前日期today = datetime.date.today()print(today)   #2018-07-05# 获取当前时间并格式化time_now = time.strftime("%Y-%m-%d %H:%M:%S",time.localtime(time.time()))print(time_now)   #2018-07-05 14:20:55# 对时间戳格式化a = 1502691655time_a = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(int(a))) print(time_a)    #2017-08-14 14:20:55# 字符串转为datetime类型str = "2018-07-01 00:00:00"datetime.datetime.strptime(st, "%Y-%m-%d %H:%M:%S")# 将时间转化为时间戳time_line = "2018-07-16 10:38:50"time_tuple = time.strptime(time_line, "%Y-%m-%d %H:%M:%S")time_line2 = int(time.mktime(time_tuple))# 明天的日期today = datetime.date.today()tomorrow = today + datetime.timedelta(days=1)print(tomorrow)   #2018-07-06# 三天前的时间today = datetime.datetime.today()tomorrow = today + datetime.timedelta(days=-3)print(tomorrow)   #2018-07-02 13:37:00.107703# 计算时间差start = "2018-07-03 00:00:00"time_now = datetime.datetime.now()b = datetime.datetime.strptime(start,'%Y-%m-%d %H:%M:%S')minutes = (time_now-b).seconds/60days = (time_now-b).daysall_minutes = days*24*60+minutesprint(minutes)   #821.7666666666667print(days)   #2print(all_minutes)   #3701.7666666666664

数据库操作

import pymysqlconn = pymysql.connect(host='10.0.8.81', port=3306, user='root', passwd='root',db='xxx', charset='utf8')cur = conn.cursor()insert_sql = "insert into tbl_name(id,name,age) values(%s,%s,%s)id = 1name = "like"age = 26data_list = []data = (id,name,age)# 单条插入cur.execute(insert_sql,data)conn.commit()# 批量插入data_list.append(data)cur.executemany(insert_sql,data_list)conn.commit()#特殊字符处理(name中含有特殊字符)data = (id,pymysql.escape_string(name),age)#更新update_sql = "update tbl_name set content = '%s' where id = "+str(id)cur.execute(update_sql%(pymysql.escape_string(content)))conn.commit()#批量更新update_sql = "UPDATE tbl_recieve SET content = %s ,title = %s , is_spider = %s WHERE id = %s"update_data = (contents,title,is_spider,one_new[0])update_data_list.append(update_data)if len(update_data_list) > 500:try:  cur.executemany(update_sql,update_data_list)   conn.commit()

总结

以上就是这篇文章的全部内容了，希望本文的内容对大家的学习或者工作具有一定的参考学习价值，谢谢大家的支持。如果你想了解更多相关内容请查看下面相关链接


  • 上一条：
    python3实现指定目录下文件sha256及文件大小统计
    下一条：
    Python使用paramiko操作linux的方法讲解

    • 昵称：

    邮箱：

    0条评论 (评论内容有缓存机制,请悉知!)
    Top

    Copyright·© 2019 侯体宗版权所有· 粤ICP备20027696号 PHP交流群

    侯体宗的博客