Python常用爬蟲代碼總結方便查詢

發布時間：2020-09-27 19:17:48 來源：腳本之家閱讀：171 作者：Lee_Tech 欄目：開發技術

beautifulsoup解析頁面

from bs4 import BeautifulSoup
soup = BeautifulSoup(htmltxt, "lxml")
# 三種裝載器
soup = BeautifulSoup("<a></p>", "html.parser")
### 只有起始標簽的會自動補全，只有結束標簽的會自動忽略
### 結果為：<a></a>
soup = BeautifulSoup("<a></p>", "lxml")
### 結果為：<html><body><a></a></body></html>
soup = BeautifulSoup("<a></p>", "html5lib")
### html5lib則出現一般的標簽都會自動補全
### 結果為：<html><head></head><body><a><p></p></a></body></html>
# 根據標簽名、id、class、屬性等查找標簽
### 根據class、id、以及屬性alog-action的值和標簽類別查詢
soup.find("a",class_="title",id="t1",attrs={"alog-action": "qb-ask-uname"}))
### 查詢標簽內某屬性的值
pubtime = soup.find("meta",attrs={"itemprop":"datePublished"}).attrs['content']
### 獲取所有class為title的標簽
for i in soup.find_all(class_="title"):
  print(i.get_text())
### 獲取特定數量的class為title的標簽
for i in soup.find_all(class_="title",limit = 2):
  print(i.get_text())
### 獲取文本內容時可以指定不同標簽之間的分隔符，也可以選擇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)
#結果為：The Dormouses story|The Dormouses story
### 獲取class為title的p標簽的id
soup.find(class_="title").get("id")
### 對class名稱正則：
soup.find_all(class_=re.compile("tit"))
### recursive參數，recursive=False時，只find當前標簽的第一級子標簽的數據
soup = BeautifulSoup('<html><head><title>abc','lxml')
soup.html.find_all("title", recursive=False)

unicode編碼轉中文

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

url encode的解碼與解碼

from urllib import parse
# 編碼
x = "中國你好"
y = parse.quote(x)
print(y)
# 解碼
x = parse.unquote(y)
print(x)

html轉義字符的解碼

from html.parser import HTMLParser
htmls = "&lt;div&gt;&lt;p&gt;"
txt = HTMLParser().unescape(htmls)
print(txt)  . # 輸出<div><p>

base64的編碼與解碼

import base64
# 編碼
content = "測試轉碼文本123"
contents_base64 = base64.b64encode(content.encode('utf-8','ignore')).decode("utf-8")
# 解碼
contents = base64.b64decode(contents_base64)

過濾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)

完全過濾script和style標簽

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

過濾html的標簽，但保留標簽里的內容

import re
htmls = "<p>abc</p>"
dr = re.compile(r'<[^>]+>',re.S)
htmls2 = dr.sub('',htmls)
print(htmls2)  #abc
正則提取內容（一般處理json）
rollback({
 "response": {
 "code": "0",
 "msg": "Success",
 "dext": ""
 },
 "data": {
 "count": 3,
 "page": 1,
 "article_info": [{
  "title": "“小庫里”：適應比賽是首要任務 投籃終會找到節奏",
  "url": "http:\/\/sports.qq.com\/a\/20180704\/035378.htm",
  "time": "2018-07-04 16:58:36",
  "column": "NBA",
  "img": "",
  "desc": ""
 }, {
  "title": "首鋼體育助力國家冰球集訓隊 中國冰球聯賽年底啟動",
  "url": "http:\/\/sports.qq.com\/a\/20180704\/034698.htm",
  "time": "2018-07-04 16:34:44",
  "column": "綜合體育",
  "img": "",
  "desc": ""
 }...]
 }
})
import re
# 提取這個json中的每條新聞的title、url
# (.*?)為要提取的內容，可以在正則字符串中加入.*？表示中間省略若干字符
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]

時間操作

# 獲取當前日期
today = datetime.date.today()
print(today)   #2018-07-05
# 獲取當前時間并格式化
time_now = time.strftime("%Y-%m-%d %H:%M:%S",time.localtime(time.time()))
print(time_now)   #2018-07-05 14:20:55
# 對時間戳格式化
a = 1502691655
time_a = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(int(a))) 
print(time_a)    #2017-08-14 14:20:55
# 字符串轉為datetime類型
str = "2018-07-01 00:00:00"
datetime.datetime.strptime(st, "%Y-%m-%d %H:%M:%S")
# 將時間轉化為時間戳
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
# 三天前的時間
today = datetime.datetime.today()
tomorrow = today + datetime.timedelta(days=-3)
print(tomorrow)   #2018-07-02 13:37:00.107703
# 計算時間差
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/60
days = (time_now-b).days
all_minutes = days*24*60+minutes
print(minutes)   #821.7666666666667
print(days)   #2
print(all_minutes)   #3701.7666666666664

數據庫操作

import pymysql
conn = 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 = 1
name = "like"
age = 26
data_list = []
data = (id,name,age)
# 單條插入
cur.execute(insert_sql,data)
conn.commit()
# 批量插入
data_list.append(data)
cur.executemany(insert_sql,data_list)
conn.commit()
#特殊字符處理(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()

總結

以上就是這篇文章的全部內容了，希望本文的內容對大家的學習或者工作具有一定的參考學習價值，謝謝大家對億速云的支持。如果你想了解更多相關內容請查看下面相關鏈接

向AI問一下細節

91超碰碰碰碰久久久久久综合_超碰av人澡人澡人澡人澡人掠_国产黄大片在线观看画质优化_txt小说免费全本

Python常用爬蟲代碼總結方便查詢

猜你喜歡

91超碰碰碰碰久久久久久综合_超碰av人澡人澡人澡人澡人掠_国产黄大片在线观看画质优化_txt小说免费全本

Python常用爬蟲代碼總結方便查詢

猜你喜歡

最新資訊

相關推薦

相關標簽