爬虫常用正则表达式

1.指定开头，指定结尾

str1 = "background-image: url(https://image2.pearvideo.com/cont/20200428/cont-1671582-12370181.png);"

# \b开头字符.*?结尾字符\b

res = re.search(r"\bhttp.*?png\b", str1)
# 或者
res = re.search(r"http(.*?)png",str1)
print(res.group())

2.匹配所有整型数字

inventory_count = "库存5000"
res = re.search("\d+", inventory_count)

3.匹配所有浮点数

 price = 565656.23223  
 price = re.search('[-+]?[0-9]*\.?[0-9]+', price)

 

4.匹配无视空格和换行

str1 = "instrt into inswate"
text_data = "hjkshcsdk dsehfhk instrt      into 
inswate "
str1_list = str1.split(" ")
str2 = ""
for i in str1_list:
     str2 = str2 + r"%s(\s*)(?i)" % i
     str3 = "(?s)(?i)" + str2
     response = re.search(str3.rstrip("(\s*)(?i)"), text_data)

 5.匹配或者

(png|jpg|jpeg) 就是或的关系

images = re.search(r"\bhttp.*?(png|jpg|jpeg)\b", image)

 6.匹配所有中文

text1_list = re.findall('[^\x00-\xff]',text1)

 7.匹配小数或者整数

count_list = re.findall('(\d+\.\d+|\d+)',desc1)