东方财富网高效爬虫：获取全面信息

import urllib
import urllib.request
import re
import xlwt

book = xlwt.Workbook(encoding='utf-8', style_compression=0)
sheet = book.add_sheet('data', cell_overwrite_ok=True)

for j in range(1, 10): #自己选择爬取的页数，此处选择10
    print(j)

    url = 'http://guba.eastmoney.com/list,000802_{0}.html'.format(j)
    try:
        request = urllib.request.Request(url)
        response = urllib.request.urlopen(request)
        content = response.read().decode('utf-8')
        pattern1 = re.compile('<span class="l5 a5".*?>(.*?)</span>', re.S)
        time = re.findall(pattern1, content)#爬取股评的发表时间
        pattern2 = re.compile('<span class="l3 a3".*?><a href.*?>(.*?)</a>', re.S)
        comment = re.findall(pattern2, content)#爬取股评的内容
        pattern3 = re.compile('<span class="l4 a4".*?><a href.*?><font.*?>(.*?)</font>', re.S)
        author = re.findall(pattern3, content)#爬取股评的发表作者
        pattern4 = re.compile('<span class="l2 a2".*?>(.*?)</span>', re.S)
        num_comment = re.findall(pattern4, content)#爬取股评的评论数
        pattern5 = re.compile('<span class="l1 a1".*?>(.*?)</span>', re.S)
        num_read = re.findall(pattern5, content)#爬取股评的阅读数

        p = len(author)
        for i in range(0, p):
            comment_time = time[i]