1 # 查找发贴版面并记录版面信息
 2 while page_num < url[topical]:
 3     content = get_url_content(now_url)
 4     page_num += 1
 5     page_str = str(page_num)
 6     now_url = base_url + page_str    # 构造爬虫的网页链接
 7     soup = BeautifulSoup(content, 'html.parser') # 用BeautifulSoup提取网页中的文本内容
 8     i = 0
 9     name = 'VChart'
10     while i < 20:
11         # 查找标签获取贴主id
12         new_name = soup.find_all("li")[i].next_element.next_sibling.next_element.next_element.next_element
13
14         # 若查找到一条记录就记录信息并跳出循环进行下一版面的查找
15         if new_name == name:
16             f.write("\'" + topical + "\'" + ": " + str(url[topical]) + ", ")
17             i = 21
18             page_num = url[topical] + 1
19         elif new_name is None:
20             i = 21
21     i += 1

 1 # 爬取每个版面的贴主的帖子并写入文件
 2 now_url = base_url + page_str    # 构造爬虫网页链接
 3 soup = BeautifulSoup(content, 'html.parser')    # 使用BeautifulSoup提取网页中的文本信息
 4 i = 0
 5 name = 'VChart'
 6 while i < 20:
 7     # 获取每一页所有的贴主id
 8     new_name = soup.find_all("li")[i].next_element.next_sibling.next_element.next_element.next_element
 9
10     if new_name == name:
11         new_url = base_url_+soup.find_all("li")[i].next_element.next_element.get('href')
12         f.write(new_url)
13         f.write("\n")
14
15         content_ = get_url_content(new_url)
16         soup1 = BeautifulSoup(content_, 'html.parser')
17         s = soup1.select(".sp")
18         f.write(s[2].previous_sibling()[0].get_text())
19         l = len(s)
20         j = 2
21         while j < l-2:
22             s1 = s[j].get_text()
23             j += 1
24             f.write(s1)
25         time.sleep(1)
26     i += 1

 1 # 根据一段帖子文本中的时间信息排序，返回一个list
 2 def list_sort(list1):
 3     pattern = re.compile("[0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}:[0-9]{2}")
 4
 5     print(list1)
 6     list2 = re.findall(pattern, str(list1))
 7     list3 = list(zip(list2, list1))
 8     list3 = sorted(list3, key=lambda item: item[0])
 9     list4 = []
10     for temp in list3:
11         list4.append(temp[1])
12     return list4

 1 # 分词写并写入文件
 2 def segmented(file, text):
 3     ans = re.sub('[^\w\u4e00-\u9fff]+', "", text)  # 正则表达式过滤出汉字
 4     ans = "".join(ans.split())
 5     # seg_list = jieba.cut(ans)  # 精确模式（默认是精确模式）
 6     # print("[精确模式]: ", "/ ".join(seg_list))
 7     words = jieba.cut(ans, cut_all=False)
 8     word_freq = {}
 9     stopwords = stopwordslist('ting.txt')    # 去除停用词
10     for word in words:
11         if word in word_freq:
12             word_freq[word] += 1
13         else:
14             word_freq[word] = 1
15
16     freq_word = []
17     for word, freq in word_freq.items():
18         freq_word.append((word, freq))
19     freq_word.sort(key=lambda x: x[1], reverse=True)

1 # Excel文件读写操作
2 readbook = xlrd.open_workbook(r'统计_all.xlsx')
3 sheet = readbook.sheet_by_name('Sheet1')
4 nrows = sheet.nrows
5 f = xlwt.Workbook(encoding='utf-8')
6 table = f.add_sheet('data')
7
8 table.write(i, j, 0)
9 f.save("统计.xls")