python爬虫笔记(3-1)re模块实例

 实例来源:https://www.bilibili.com/video/BV1i54y1h75W?p=1

# 爬取首页必看片电影中的名称+下载链接 
import requests
import re

# 获取首页源码
domain = 'https://www.dy2018.com/'
resp = requests.get(domain, verify = False)  #verify = False去掉安全验证
resp.encoding = 'gbk'  #指定字符集
# print(resp.text)

# 预加载正则,提取首页面所需信息(片名&链接)
obj1 = re.compile(r"2021新片精品.*?<ul>(?P<name_link>.*?)</ul>",re.S)
result1 = obj1.search(resp.text)
# print(result1.group("name"))
homepage_content = result1.group("name_link")

# 拼接子页面完整链接 :预加载正则,提取片名&链接中的链接,与domain组成完整的子页面链接(域名+地址)
obj2 = re.compile(r"<li><a href='(?P<href>.*?)'",re.S)
result2 = obj2.finditer(homepage_content)
child_href_list = []
for i in result2:
    child_href = domain +i.group("href").strip("/")
    # print(child_href)
    child_href_list.append(child_href) #将拼接好的子页面地址存入list中便于后面提取
# print(child_href_list)

# 通过子页面地址,获取子页面源码
# 在子页面源码中提取所需内容(片名+下载地址):预加载正则,提取所需内容
obj3 = re.compile(r'◎译  名(?P<trans_name>.*?)<br />◎片  名(?P<movie_name>.*?)<br />.*?'
                  r'<td style="WORD-WRAP: break-word" bgcolor="#fdfddf"><a href="(?P<download>.*?)">',re.S)
for ii in child_href_list:
    child_respon = requests.get(ii)
    child_respon.encoding = 'gbk'
    # print(child_respon.text)
    result3 = obj3.search(child_respon.text)
    print(result3.group("trans_name"))
    print(result3.group("movie_name"))
    print(result3.group("download"))

 

上一篇:react 文件下载


下一篇:hash路由微信公众号支付提示当前页面URL未注册