[python爬虫]常用user_agent.py

在分布式爬虫中,为了获取多样的爬虫信息,我们通常会采用不同的user_agent去访问,我在这里提供了一些user_agent

import random
# pc端的user-agent
user_agent_pc = [
    # 谷歌
    'Mozilla/5.0.html (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.html.2171.71 Safari/537.36',
    'Mozilla/5.0.html (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.html.1271.64 Safari/537.11',
    'Mozilla/5.0.html (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.html.648.133 Safari/534.16',
    # 火狐
    'Mozilla/5.0.html (Windows NT 6.1; WOW64; rv:34.0.html) Gecko/20100101 Firefox/34.0.html',
    'Mozilla/5.0.html (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10',
    # opera
    'Mozilla/5.0.html (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.html.2171.95 Safari/537.36 OPR/26.0.html.1656.60',
    # qq浏览器
    'Mozilla/5.0.html (compatible; MSIE 9.0.html; Windows NT 6.1; WOW64; Trident/5.0.html; SLCC2; .NET CLR 2.0.html.50727; .NET CLR 3.5.30729; .NET CLR 3.0.html.30729; Media Center PC 6.0.html; .NET4.0C; .NET4.0E; QQBrowser/7.0.html.3698.400)',
    # 搜狗浏览器
    'Mozilla/5.0.html (Windows NT 5.1) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.html.963.84 Safari/535.11 SE 2.X MetaSr 1.0.html',
    # 360浏览器
    'Mozilla/5.0.html (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.html.1599.101 Safari/537.36',
    'Mozilla/5.0.html (Windows NT 6.1; WOW64; Trident/7.0.html; rv:11.0.html) like Gecko',
    # uc浏览器
    'Mozilla/5.0.html (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.html.2125.122 UBrowser/4.0.html.3214.0.html Safari/537.36',
]
# 移动端的user-agent
user_agent_phone = [
    # IPhone
    'Mozilla/5.0.html (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.html.2 Mobile/8J2 Safari/6533.18.5',
    # IPAD
    'Mozilla/5.0.html (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.html.2 Mobile/8C148 Safari/6533.18.5',
    'Mozilla/5.0.html (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.html.2 Mobile/8J2 Safari/6533.18.5',
    # Android
    'Mozilla/5.0.html (Linux; U; Android 2.2.1; zh-cn; HTC_Wildfire_A3333 Build/FRG83D) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0.html Mobile Safari/533.1',
    'Mozilla/5.0.html (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0.html Mobile Safari/533.1',
    # QQ浏览器 Android版本
    'MQQBrowser/26 Mozilla/5.0.html (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0.html Mobile Safari/533.1',
    # Android Opera Mobile
    'Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10',
    # Android Pad Moto Xoom
    'Mozilla/5.0.html (Linux; U; Android 3.0.html; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0.html Safari/534.13',
]

def get_user_agent_pc():
    return random.choice(user_agent_pc)

def get_user_agent_phone():
    return random.choice(user_agent_phone)
  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 1
    评论
好的,我会为该py文件增加注释。以下是注释后的代码: ```python import requests from bs4 import BeautifulSoup import time import random import re # 获取页面内容 def get_html(url): # 添加请求头,模拟浏览器请求 headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'} try: r = requests.get(url, headers=headers) r.raise_for_status() r.encoding = r.apparent_encoding return r.text except: return "" # 获取书籍页面URL列表 def get_book_urls(start_url): book_urls = [] # 循环获取每一页的书籍URL for i in range(0, 250, 25): url = start_url + '?start=' + str(i) html = get_html(url) soup = BeautifulSoup(html, 'html.parser') tags = soup('a', {'class': 'title'}) for tag in tags: book_url = tag.get('href') book_urls.append(book_url) # 每爬取一次页面,随机休眠1-3秒,避免被封IP time.sleep(random.randint(1, 3)) return book_urls # 获取书籍名称 def get_book_name(soup): name = soup.find('h1').string return name # 获取书籍评分 def get_book_rate(soup): rate = soup.find('strong', {'class': 'll rating_num'}).string return rate # 获取书籍评论数 def get_book_comment_count(soup): count = soup.find('a', {'class': 'rating_people'}).find('span').string return count # 获取书籍标签 def get_book_tags(soup): tags = [] tag_list = soup.find('div', {'id': 'db-tags-section'}).find_all('a') for tag in tag_list: tags.append(tag.string) return tags # 获取书籍评论 def get_book_comments(book_url): comments = [] html = get_html(book_url + 'comments/') soup = BeautifulSoup(html, 'html.parser') # 获取评论翻页URL列表 page_urls = [] paging = soup.find('div', {'class': 'paging'}) if paging: page_list = paging.find_all('a') for page in page_list: page_urls.append(page.get('href')) # 循环获取每一页的评论 for page_url in set(page_urls): html = get_html(page_url) soup = BeautifulSoup(html, 'html.parser') comment_list = soup.find_all('div', {'class': 'comment-item'}) for comment in comment_list: # 获取评论内容 content = comment.p.get_text().strip() # 去除空格和换行符 content = re.sub(r'[\n\s+]','',content) # 去除中英文标点符号 content = re.sub(r'[^\w\s]','',content) if content: comments.append(content) # 每爬取一次页面,随机休眠1-3秒,避免被封IP time.sleep(random.randint(1, 3)) return comments # 获取书籍信息 def get_book_info(book_url): html = get_html(book_url) soup = BeautifulSoup(html, 'html.parser') name = get_book_name(soup) rate = get_book_rate(soup) count = get_book_comment_count(soup) tags = get_book_tags(soup) comments = get_book_comments(book_url) book_info = {'name': name, 'rate': rate, 'count': count, 'tags': tags, 'comments': comments} return book_info if __name__ == '__main__': start_url = 'https://book.douban.com/top250' book_urls = get_book_urls(start_url) book_infos = [] # 循环获取每本书籍的信息 for book_url in book_urls: book_info = get_book_info(book_url) book_infos.append(book_info) # 每爬取一本书籍,随机休眠1-3秒,避免被封IP time.sleep(random.randint(1, 3)) # 保存数据到文件 with open('book_info.txt', 'w', encoding='utf-8') as f: for book_info in book_infos: f.write(str(book_info) + '\n') ``` 注释已添加在代码中,希望可以帮助您更好地理解代码。

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值