python爬虫爬取百度文档

def get_num(url):

response = requests.get(url, headers=headers).text

result = re.search(

r’&md5sum=(.)&sign=(.)&rtcs_flag=(.)&rtcs_ver=(.?)“.rsign":"(.?)”,', response, re.M | re.I) # 寻找参数

reader = {

“md5sum”: result.group(1),

“sign”: result.group(2),

“rtcs_flag”: result.group(3),

“rtcs_ver”: result.group(4),

“width”: 176,

“type”: “org”,

“rsign”: result.group(5)

}

result_page = re.findall(

r’merge":"(.?)".?“page”😦.*?)}', response) # 获取每页的标签

doc_url = “https://wkretype.bdimg.com/retype/merge/” + url[29:-5] # 网页的前缀

n = 0

for i in range(len(result_page)): # 最大同时一次爬取10页

if i % 10 is 0:

doc_range = ‘_’.join([k for k, v in result_page[n:i]])

reader[‘pn’] = n + 1

reader[‘r