# 正則表達(dá)式, 按照一定規(guī)則提取字符串中的符合條件的內(nèi)容
 str1='ghmjfdhngbrghmgjhngbfrthnhfgbfv'
 list1=re.findall('gj(.*?)fr',str1)   #返回值是列表
 print(list1)
 
 str2 = '''hellobtevrqtyjumuynthbg
 mybrtymuntbrgev
 juntybrwtvewbynutybworld'''
 list1 = re.findall('hello(.*?)world', str2, re.S)  # re.S允許跨行匹配
 print(list1)

爬取全書網(wǎng)小說

 import os
 import re
 import requests
 
 url = 'http://www.quannovel.com/read/620/'  # 需要進(jìn)行爬蟲的網(wǎng)址
 req = requests.post(url)  # 訪問網(wǎng)頁,獲取網(wǎng)頁內(nèi)容
 book_name = re.findall('(.*?)(.*?)', req.text)  # 獲取章節(jié)名
 
 url_list = re.findall('<a href="(.*?).html', req.text)  # 獲取正文網(wǎng)址
 
 dict1 = {}
 for i in range(len(title_list)):
     dict1[title_list[i]] = f'{url}{url_list[i]}.html'  # 將目錄和網(wǎng)址放到字典里
 
 if not os.path.exists(f'D:/{book_name}'):  # 如果沒有以書名命名的目錄,新建目錄
     os.mkdir(f'D:/{book_name}')
 
 count = 1
 for k, v in dict1.items():
     if count > 5:
         break
     else:
         req = requests.get(v)  # 訪問正文網(wǎng)頁
         text = re.findall('class="page-content ">(.*?)<div class', req.text, re.S)[0]  # 獲取文章內(nèi)容
         text = text.replace('', '').replace('', '')
         with open(f'd:/{book_name}/{k}.txt','w+') as file1:
             file1.write(text)
     print(f'第{count}章爬取完畢')
     count += 1