| 13 | |
| 14 | |
| 15 | class CommentParser(Parser): |
| 16 | def __init__(self, cookie, weibo_id): |
| 17 | self.cookie = cookie |
| 18 | self.url = 'https://weibo.cn/comment/' + weibo_id |
| 19 | self.selector = handle_html(self.cookie, self.url) |
| 20 | |
| 21 | def get_long_weibo(self): |
| 22 | """获取长原创微博""" |
| 23 | try: |
| 24 | for i in range(5): |
| 25 | self.selector = handle_html(self.cookie, self.url) |
| 26 | if self.selector is not None: |
| 27 | info_div = self.selector.xpath("//div[@class='c' and @id='M_']")[0] |
| 28 | info_span = info_div.xpath("//span[@class='ctt']")[0] |
| 29 | # 1. 获取 info_span 中的所有 HTML 代码作为字符串 |
| 30 | html_string = etree.tostring(info_span, encoding='unicode', method='html') |
| 31 | # 2. 将 <br> 替换为 \n |
| 32 | html_string = html_string.replace('<br>', '\n') |
| 33 | # 3. 去掉所有 HTML 标签，但保留标签内的有效文本 |
| 34 | new_content = fromstring(html_string).text_content() |
| 35 | # 4. 替换多个连续的 \n 为一个 \n |
| 36 | new_content = re.sub(r'\n+\s*', '\n', new_content) |
| 37 | weibo_content = handle_garbled(new_content) |
| 38 | if weibo_content is not None: |
| 39 | return weibo_content |
| 40 | sleep(random.randint(6, 10)) |
| 41 | except Exception: |
| 42 | logger.exception(u'网络出错') |
| 43 | |
| 44 | def get_long_retweet(self): |
| 45 | """获取长转发微博""" |
| 46 | return self.get_long_weibo() |
| 47 | |
| 48 | def get_video_page_url(self): |
| 49 | """获取微博视频页面的链接""" |
| 50 | video_url = '' |
| 51 | try: |
| 52 | self.selector = handle_html(self.cookie, self.url) |
| 53 | if self.selector is not None: |
| 54 | # 来自微博视频号的格式与普通格式不一致，不加 span 层级 |
| 55 | links = self.selector.xpath("body/div[@class='c' and @id][1]/div//a") |
| 56 | for a in links: |
| 57 | if 'm.weibo.cn/s/video/show?object_id=' in a.xpath( |
| 58 | '@href')[0]: |
| 59 | video_url = a.xpath('@href')[0] |
| 60 | break |
| 61 | except Exception: |
| 62 | logger.exception(u'网络出错') |
| 63 | |
| 64 | return video_url |
no outgoing calls