python 爬取百度云资源
pan1
import urllib.request
import re
import random
def get_source(key):
print('请稍等，爬取中....')
headers = [{'User-Agent':'Mozilla/5.0 (Windows NT 6.3 WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Maxthon/4.4.8.1000 Chrome/30.0.1599.101 Safari/537.36'},{'User-Agent':"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:45.0) Gecko/20100101 Firefox/45.0"},{'User-Agent': 'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 10.0; WOW64; Trident/7.0)'}]
header = random.choice(headers) # 随机选取一个header
keyword = key.encode('utf-8')
keyword = urllib.request.quote(keyword) # 对关键词进行编码
# 这里是关键，称随机搜索一个资源名，然后对其结果网址进行分析
url = "http://www.wangpansou.cn/s.php?wp=0&ty=gn&op=gn&q="+keyword+"&q="+keyword
req = urllib.request.Request(url, headers=header)
html = urllib.request.urlopen(req)
# 编码类型
head_type = html.headers['Content-Type'].split('=')[-1]
status = html.getcode() # 获取状态码，只有访问成功了才继续。
if status == 200:
html = html.read()
html = html.decode(head_type) # 根据网站编码时行解码
# 正则匹配
pattern = re.compile('<a href="(.+)"><div tabindex="\d{1,3}">\d{1,3}</div></a>')
content = pattern.findall(html)
url_list = []
url_head = 'http://www.wangpansou.cn/'
for i in content:
i = url_head +i # 因为正匹配出来的只有一部分,所以把前面的一部分加上,开成完整的链接
if not i in url_list: # 去掉重复的,网页确实有两分,所以去重.
url_list.append(i) # 得到所有 有搜索结果的页面网址列表
count = 1# 计数用
for each_url in url_list:
header = random.choice(headers) # 针对每个链接都随机选择一个'头',防止被服务器封掉
request1 = urllib.request.Request(each_url, headers=header)
html2 = urllib.request.urlopen(request1)
status = html2.getcode() # 获取状态码
if status == 200:
html2 = html2.read()
html2 = html2.decode(head_type)
pattern1 = re.compile('<a href="(.+)"> content1 = pattern1.findall(html2)
pattern2 = re.compile('<div>\s+(.+)')
content2 = pattern2.findall(html2)
for i in range(0,len(content2)):
print(str(count) + ':' + content2 + '\n' + content1)
print()
count += 1
print('共搜索到%d个资源,已经全部爬取完毕！' % count)
if __name__ == '__main__':
get_source(input('请输入要搜索的资源名:'))
说明：
a.本搜索实际是通过通过网盘搜这个网站进行的二次搜索，如果找资源也可以直接到网盘搜进行一页一页的搜索
本脚本唯一的优点是一次性将所有结果全部爬下来，不用一页一页的翻找。
b.代码相当丑，但这也是对学习过程的记录，先实现功能，再考虑代码。
"""
略作优化，同时修正了两个小bug
按 Ctrl+C 复制代码
pan2
# coding = 'utf-8'
import urllib.request
import re
import random
def get_html(url, header):
req = urllib.request.Request(url, headers=header)
html = urllib.request.urlopen(req)
head_type = html.headers['Content-Type'].split('=')[-1]
status = html.getcode()
return html, head_type, status # 分别得到html, 编码方式， 访问状态码
headers = [{'User-Agent':'Mozilla/5.0 (Windows NT 6.3 WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Maxthon/4.4.8.1000 Chrome/30.0.1599.101 Safari/537.36'},{'User-Agent':"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:45.0) Gecko/20100101 Firefox/45.0"},{'User-Agent': 'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 10.0; WOW64; Trident/7.0)'}]
keyword =input('请输入要搜索的资源名:')
keyword = urllib.request.quote(keyword.encode('utf-8'))
url = "http://www.wangpansou.cn/s.php?wp=0&ty=gn&op=gn&q="+keyword+"&q="+keyword
header = random.choice(headers)
f_html, f_head_type, f_status = get_html(url, header)
if f_status == 200:
f_html = f_html.read()
f_html = f_html.decode(f_head_type)
pattern = re.compile('<a href="(.+)"><div tabindex="\d{1,3}">\d{1,3}</div></a>')
content = pattern.findall(f_html) # 得到所有有相关结果的页面链接
url_list = []
url_head = 'http://www.wangpansou.cn/'
for i in content:
i = url_head +i # 因为正匹配出来的只有一部分,所以把前面的一部分加上,开成完整的链接
if not i in url_list: # 去掉重复的,网页确实有两分,所以去重.
url_list.append(i) # 得到所有 有搜索结果的页面网址列表
first_url = url_list[:-2] + '0'# 加上第一页
url_list.insert(0,first_url)
count = 0
for each_url in url_list:
header = random.choice(headers)
s_html, s_head_type, s_status = get_html(each_url, header)
if s_status == 200:
s_html = s_html.read()
s_html = s_html.decode(s_head_type)
s_pattern = re.compile('<a href="(.+)"> s_content = s_pattern.findall(s_html) # 分享的链接
t_pattern = re.compile('<div>\s+(.+)')
t_content = t_pattern.findall(s_html) # 文件信息
else:
print('Website Error!')
for i in range(0, len(s_content)):
count += 1
print(str(count) + ':' + t_content + '\n' + s_content)
print()
print('共搜索到%d个资源,已经全部爬取完毕！' % count)
页:
[1]