python3[爬蟲實戰] 爬蟲之requests爬取新浪微博京東客服
阿新 • • 發佈：2018-12-31
爬取的內容為京東客服的微博及評論
思路:主要是通過手機端訪問新浪微博的api介面，然後進行資料的篩選，
這個主要是登陸上去的微博的url連結，
可以看到的介面：
這裡主要爬取的內容為：
說說，說說下面的評論條目
雖然很簡單，但是，不得不說句mmp，爬取的過程很坎坷，現在是一直在ip上，另外，個人經過嘗試，睡眠時間30秒一次也不是很好的效果， 睡眠10秒就足夠了，可能該封你的ip還是會封的，我這問題應該封ip的情況
爬取的方法主要是通過手機端api進行json資料的獲取，然後進行資料的提取。
這裡可以使用火狐fox的外掛使用：
主要api：
說說API：
類似於這樣子的，
詳情評論內容API：
在每條評論下會有一個idstr:4137390568546147
帶大家看一下評論api下返回的資料：JSON格式的
{ "cardlistInfo": { "containerid": "1076035650743478", "v_p": 42, "show_style": 1, "total": 3264, "page": 2 }, "cards": [ { "card_type": 9, "itemid": "1076035650743478_-_4137858652321796", "scheme": "https://m.weibo.cn/status/FfSSl9K0k?mblogid=FfSSl9K0k&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "mblog": { "created_at": "2小時前", "id": "4137858652321796", "mid": "4137858652321796", "idstr": "4137858652321796", "text": "明天又要上班了，用四個字描述下你現在的心情吧<span class=\"url-icon\"><img src=\"//h5.sinaimg.cn/m/emoticon/icon/others/d_erha-0d2bea3a7d.png\" style=\"width:1em;height:1em;\" alt=\"[二哈]\"></span> ", "textLength": 50, "source": "微博 weibo.com", "favorited": false, "thumbnail_pic": "http://wx4.sinaimg.cn/thumbnail/006apWvQgy1fi7tkjguy4j309q09qt8q.jpg", "bmiddle_pic": "http://wx4.sinaimg.cn/bmiddle/006apWvQgy1fi7tkjguy4j309q09qt8q.jpg", "original_pic": "http://wx4.sinaimg.cn/large/006apWvQgy1fi7tkjguy4j309q09qt8q.jpg", "user": { "id": 5650743478, "screen_name": "京東客服", "profile_image_url": "https://tva4.sinaimg.cn/crop.38.7.206.206.180/006apWvQjw8f9dwuejt68j307y0630sz.jpg", "profile_url": "https://m.weibo.cn/u/5650743478?uid=5650743478&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "statuses_count": 3245, "verified": true, "verified_type": 2, "verified_type_ext": 0, "verified_reason": "北京京東世紀貿易有限公司", "description": "訂單諮詢、問題反饋、意見建議……獲取專業貼心服務，盡在京東客服", "gender": "f", "mbtype": 2, "urank": 29, "mbrank": 2, "follow_me": false, "following": false, "followers_count": 18427, "follow_count": 235, "cover_image_phone": "https://tva4.sinaimg.cn/crop.0.0.640.640.640/006apWvQjw1f2g20q03tbj30e80e8t93.jpg" }, "reposts_count": 0, "comments_count": 4, "attitudes_count": 2, "isLongText": false, "visible": { "type": 0, "list_id": 0 }, "mblogtype": 0, "bid": "FfSSl9K0k", "pics": [ { "pid": "006apWvQgy1fi7tkjguy4j309q09qt8q", "url": "https://wx4.sinaimg.cn/orj360/006apWvQgy1fi7tkjguy4j309q09qt8q.jpg", "size": "orj360", "geo": { "width": "350", "height": "350", "croped": false }, "large": { "size": "large", "url": "https://wx4.sinaimg.cn/large/006apWvQgy1fi7tkjguy4j309q09qt8q.jpg", "geo": { "width": "350", "height": "350", "croped": false } } } ] }, "show_type": 0, "openurl": "" }, { "card_type": 9, "itemid": "1076035650743478_-_4137692553365577", "scheme": "https://m.weibo.cn/status/FfOyre7xv?mblogid=FfOyre7xv&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "mblog": { "created_at": "13小時前", "id": "4137692553365577", "mid": "4137692553365577", "idstr": "4137692553365577", "text": "你覺得舉辦哪種《中國有_____》比賽，你能進入決賽？ ", "textLength": 49, "source": "微博 weibo.com", "favorited": false, "thumbnail_pic": "http://wx2.sinaimg.cn/thumbnail/006apWvQgy1fi7ul9n9rfj30k00lsgnj.jpg", "bmiddle_pic": "http://wx2.sinaimg.cn/bmiddle/006apWvQgy1fi7ul9n9rfj30k00lsgnj.jpg", "original_pic": "http://wx2.sinaimg.cn/large/006apWvQgy1fi7ul9n9rfj30k00lsgnj.jpg", "user": { "id": 5650743478, "screen_name": "京東客服", "profile_image_url": "https://tva4.sinaimg.cn/crop.38.7.206.206.180/006apWvQjw8f9dwuejt68j307y0630sz.jpg", "profile_url": "https://m.weibo.cn/u/5650743478?uid=5650743478&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "statuses_count": 3245, "verified": true, "verified_type": 2, "verified_type_ext": 0, "verified_reason": "北京京東世紀貿易有限公司", "description": "訂單諮詢、問題反饋、意見建議……獲取專業貼心服務，盡在京東客服", "gender": "f", "mbtype": 2, "urank": 29, "mbrank": 2, "follow_me": false, "following": false, "followers_count": 18427, "follow_count": 235, "cover_image_phone": "https://tva4.sinaimg.cn/crop.0.0.640.640.640/006apWvQjw1f2g20q03tbj30e80e8t93.jpg" }, "reposts_count": 0, "comments_count": 13, "attitudes_count": 1, "isLongText": false, "visible": { "type": 0, "list_id": 0 }, "mblogtype": 0, "bid": "FfOyre7xv", "pics": [ { "pid": "006apWvQgy1fi7ul9n9rfj30k00lsgnj", "url": "https://wx2.sinaimg.cn/orj360/006apWvQgy1fi7ul9n9rfj30k00lsgnj.jpg", "size": "orj360", "geo": { "width": 360, "height": 392, "croped": false }, "large": { "size": "large", "url": "https://wx2.sinaimg.cn/large/006apWvQgy1fi7ul9n9rfj30k00lsgnj.jpg", "geo": { "width": "720", "height": "784", "croped": false } } } ] }, "show_type": 0, "openurl": "" }, { "card_type": 9, "itemid": "1076035650743478_-_4137390568546147", "scheme": "https://m.weibo.cn/status/FfGHmzRf5?mblogid=FfGHmzRf5&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "mblog": { "created_at": "昨天 14:24", "id": "4137390568546147", "mid": "4137390568546147", "idstr": "4137390568546147", "text": "週末就是買買買，吃吃吃<span class=\"url-icon\"><img src=\"//h5.sinaimg.cn/m/emoticon/icon/default/d_huaixiao-bb5966dcc6.png\" style=\"width:1em;height:1em;\" alt=\"[壞笑]\"></span> ", "textLength": 28, "source": "微博 weibo.com", "favorited": false, "thumbnail_pic": "http://wx2.sinaimg.cn/thumbnail/006apWvQgy1fi7taijr9pg307e05kgvl.gif", "bmiddle_pic": "http://wx2.sinaimg.cn/bmiddle/006apWvQgy1fi7taijr9pg307e05kgvl.gif", "original_pic": "http://wx2.sinaimg.cn/large/006apWvQgy1fi7taijr9pg307e05kgvl.gif", "user": { "id": 5650743478, "screen_name": "京東客服", "profile_image_url": "https://tva4.sinaimg.cn/crop.38.7.206.206.180/006apWvQjw8f9dwuejt68j307y0630sz.jpg", "profile_url": "https://m.weibo.cn/u/5650743478?uid=5650743478&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "statuses_count": 3245, "verified": true, "verified_type": 2, "verified_type_ext": 0, "verified_reason": "北京京東世紀貿易有限公司", "description": "訂單諮詢、問題反饋、意見建議……獲取專業貼心服務，盡在京東客服", "gender": "f", "mbtype": 2, "urank": 29, "mbrank": 2, "follow_me": false, "following": false, "followers_count": 18427, "follow_count": 235, "cover_image_phone": "https://tva4.sinaimg.cn/crop.0.0.640.640.640/006apWvQjw1f2g20q03tbj30e80e8t93.jpg" }, "reposts_count": 0, "comments_count": 19, "attitudes_count": 1, "isLongText": false, "visible": { "type": 0, "list_id": 0 }, "mblogtype": 0, "bid": "FfGHmzRf5", "pics": [ { "pid": "006apWvQgy1fi7taijr9pg307e05kgvl", "url": "https://wx2.sinaimg.cn/orj360/006apWvQgy1fi7taijr9pg307e05kgvl.gif", "size": "orj360", "geo": { "width": "266", "height": "200", "croped": false }, "large": { "size": "large", "url": "https://wx2.sinaimg.cn/large/006apWvQgy1fi7taijr9pg307e05kgvl.gif", "geo": { "width": "266", "height": "200", "croped": false } } } ] }, "show_type": 0, "openurl": "" }, { "card_type": 9, "itemid": "1076035650743478_-_4137278329132849", "scheme": "https://m.weibo.cn/status/FfDMkCjS1?mblogid=FfDMkCjS1&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "mblog": { "created_at": "昨天 06:58", "id": "4137278329132849", "mid": "4137278329132849", "idstr": "4137278329132849", "text": "週六早呀，今天有比我起的還早的嗎<span class=\"url-icon\"><img src=\"//h5.sinaimg.cn/m/emoticon/icon/default/d_wabishi-f5765407f7.png\" style=\"width:1em;height:1em;\" alt=\"[挖鼻]\"></span> ", "textLength": 47, "source": "微博 weibo.com", "favorited": false, "thumbnail_pic": "http://wx4.sinaimg.cn/thumbnail/006apWvQgy1fi7tiv5e5qj30dc0d5dfz.jpg", "bmiddle_pic": "http://wx4.sinaimg.cn/bmiddle/006apWvQgy1fi7tiv5e5qj30dc0d5dfz.jpg", "original_pic": "http://wx4.sinaimg.cn/large/006apWvQgy1fi7tiv5e5qj30dc0d5dfz.jpg", "user": { "id": 5650743478, "screen_name": "京東客服", "profile_image_url": "https://tva4.sinaimg.cn/crop.38.7.206.206.180/006apWvQjw8f9dwuejt68j307y0630sz.jpg", "profile_url": "https://m.weibo.cn/u/5650743478?uid=5650743478&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "statuses_count": 3245, "verified": true, "verified_type": 2, "verified_type_ext": 0, "verified_reason": "北京京東世紀貿易有限公司", "description": "訂單諮詢、問題反饋、意見建議……獲取專業貼心服務，盡在京東客服", "gender": "f", "mbtype": 2, "urank": 29, "mbrank": 2, "follow_me": false, "following": false, "followers_count": 18427, "follow_count": 235, "cover_image_phone": "https://tva4.sinaimg.cn/crop.0.0.640.640.640/006apWvQjw1f2g20q03tbj30e80e8t93.jpg" }, "reposts_count": 0, "comments_count": 8, "attitudes_count": 2, "isLongText": false, "visible": { "type": 0, "list_id": 0 }, "mblogtype": 0, "bid": "FfDMkCjS1", "pics": [ { "pid": "006apWvQgy1fi7tiv5e5qj30dc0d5dfz", "url": "https://wx4.sinaimg.cn/orj360/006apWvQgy1fi7tiv5e5qj30dc0d5dfz.jpg", "size": "orj360", "geo": { "width": 273, "height": 270, "croped": false }, "large": { "size": "large", "url": "https://wx4.sinaimg.cn/large/006apWvQgy1fi7tiv5e5qj30dc0d5dfz.jpg", "geo": { "width": "480", "height": "473", "croped": false } } } ] }, "show_type": 0, "openurl": "" }, { "card_type": 9, "itemid": "1076035650743478_-_4137054743266182", "scheme": "https://m.weibo.cn/status/FfxXIdHGm?mblogid=FfxXIdHGm&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "mblog": { "created_at": "08-04", "id": "4137054743266182", "mid": "4137054743266182", "idstr": "4137054743266182", "text": "就問一句，這樣人美心善的90後小哥你們要不要？<span class=\"url-icon\"><img src=\"//h5.sinaimg.cn/m/emoticon/icon/default/d_tian-52ea252705.png\" style=\"width:1em;height:1em;\" alt=\"[舔屏]\"></span><span class=\"url-icon\"><img src=\"//h5.sinaimg.cn/m/emoticon/icon/default/d_tian-52ea252705.png\" style=\"width:1em;height:1em;\" alt=\"[舔屏]\"></span>", "source": "微博 weibo.com", "favorited": false, "user": { "id": 5650743478, "screen_name": "京東客服", "profile_image_url": "https://tva4.sinaimg.cn/crop.38.7.206.206.180/006apWvQjw8f9dwuejt68j307y0630sz.jpg", "profile_url": "https://m.weibo.cn/u/5650743478?uid=5650743478&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "statuses_count": 3245, "verified": true, "verified_type": 2, "verified_type_ext": 0, "verified_reason": "北京京東世紀貿易有限公司", "description": "訂單諮詢、問題反饋、意見建議……獲取專業貼心服務，盡在京東客服", "gender": "f", "mbtype": 2, "urank": 29, "mbrank": 2, "follow_me": false, "following": false, "followers_count": 18427, "follow_count": 235, "cover_image_phone": "https://tva4.sinaimg.cn/crop.0.0.640.640.640/006apWvQjw1f2g20q03tbj30e80e8t93.jpg" }, "retweeted_status": { "created_at": "08-04", "id": "4137016583280831", "mid": "4137016583280831", "idstr": "4137016583280831", "text": "<span class=\"url-icon\"><img src=\"//h5.sinaimg.cn/m/emoticon/icon/default/d_tian-52ea252705.png\" style=\"width:1em;height:1em;\" alt=\"[舔屏]\"></span><span class=\"url-icon\"><img src=\"//h5.sinaimg.cn/m/emoticon/icon/default/d_tian-52ea252705.png\" style=\"width:1em;height:1em;\" alt=\"[舔屏]\"></span><span class=\"url-icon\"><img src=\"//h5.sinaimg.cn/m/emoticon/icon/default/d_tian-52ea252705.png\" style=\"width:1em;height:1em;\" alt=\"[舔屏]\"></span> <a data-url=\"http://t.cn/R9S6VWV\" href=\"http://media.weibo.cn/article?object_id=1022%3A2309404137016584472707&url_type=39&object_type=article&pos=1&luicode=10000011&lfid=1076035650743478&featurecode=20000320&id=2309404137016584472707&ep=FfwYadLuD%2C1717871843%2CFfwYadLuD%2C1717871843\" data-hide=\"\"><span class=\"url-icon\"><img src=\"https://h5.sinaimg.cn/upload/2015/09/25/3/timeline_card_small_article_default.png\"></span></i><span class=\"surl-text\">90後小哥徵婚啟事</a> ", "textLength": 38, "source": "微博 weibo.com", "favorited": false, "user": { "id": 1717871843, "screen_name": "京東", "profile_image_url": "https://tvax4.sinaimg.cn/crop.0.0.480.480.180/6664a4e3ly8fffaxrnv8fj20dc0dcmy4.jpg", "profile_url": "https://m.weibo.cn/u/1717871843?uid=1717871843&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "statuses_count": 19903, "verified": true, "verified_type": 2, "verified_type_ext": 50, "verified_reason": "京東網上商城", "description": "中國最大的自營電商企業京東商城集團線上銷售家電、數碼通訊、電腦、家居百貨、服裝服飾、母嬰、圖書、食品等13大類數萬個品牌上千萬種優質商品。", "gender": "m", "mbtype": 12, "urank": 43, "mbrank": 5, "follow_me": false, "following": false, "followers_count": 4025036, "follow_count": 258, "cover_image_phone": "https://wx1.sinaimg.cn/crop.0.0.640.640.640/6664a4e3ly1fffb8torrtj20ku0ku409.jpg" }, "reposts_count": 12, "comments_count": 24, "attitudes_count": 16, "isLongText": false, "visible": { "type": 0, "list_id": 0 }, "page_info": { "page_pic": { "url": "https://wx3.sinaimg.cn/crop.0.0.617.347.1000/6664a4e3ly1fi7khoua7dj20hk09nn45.jpg" }, "page_url": "http://media.weibo.cn/article?object_id=1022%3A2309404137016584472707&url_type=39&object_type=article&pos=2&luicode=10000011&lfid=1076035650743478&featurecode=20000320&id=2309404137016584472707", "page_title": "京東", "content1": "90後小哥徵婚啟事", "content2": "", "icon": "https://h5.sinaimg.cn/upload/2016/12/28/14/feed_headlines_icon_flash20161228_2.png", "type": "article" }, "bid": "FfwYadLuD" }, "reposts_count": 0, "comments_count": 30, "attitudes_count": 1, "isLongText": false, "visible": { "type": 0, "list_id": 0 }, "mblogtype": 0, "raw_text": "就問一句，這樣人美心善的90後小哥你們要不要？[舔屏][舔屏]", "bid": "FfxXIdHGm" }, "show_type": 0, "openurl": "" }, { "card_type": 9, "itemid": "1076035650743478_-_4136952959746775", "scheme": "https://m.weibo.cn/status/FfvjxETA3?mblogid=FfvjxETA3&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "mblog": { "created_at": "08-04", "id": "4136952959746775", "mid": "4136952959746775", "idstr": "4136952959746775", "text": "週五早上上班的你和下班的你<span class=\"url-icon\"><img src=\"//h5.sinaimg.cn/m/emoticon/icon/default/d_xiaoku-7430606cb7.png\" style=\"width:1em;height:1em;\" alt=\"[笑cry]\"></span> ", "textLength": 33, "source": "微博 weibo.com", "favorited": false, "thumbnail_pic": "http://wx1.sinaimg.cn/thumbnail/006apWvQgy1fi7fkqpatfj30j60j6jsg.jpg", "bmiddle_pic": "http://wx1.sinaimg.cn/bmiddle/006apWvQgy1fi7fkqpatfj30j60j6jsg.jpg", "original_pic": "http://wx1.sinaimg.cn/large/006apWvQgy1fi7fkqpatfj30j60j6jsg.jpg", "user": { "id": 5650743478, "screen_name": "京東客服", "profile_image_url": "https://tva4.sinaimg.cn/crop.38.7.206.206.180/006apWvQjw8f9dwuejt68j307y0630sz.jpg", "profile_url": "https://m.weibo.cn/u/5650743478?uid=5650743478&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "statuses_count": 3245, "verified": true, "verified_type": 2, "verified_type_ext": 0, "verified_reason": "北京京東世紀貿易有限公司", "description": "訂單諮詢、問題反饋、意見建議……獲取專業貼心服務，盡在京東客服", "gender": "f", "mbtype": 2, "urank": 29, "mbrank": 2, "follow_me": false, "following": false, "followers_count": 18427, "follow_count": 235, "cover_image_phone": "https://tva4.sinaimg.cn/crop.0.0.640.640.640/006apWvQjw1f2g20q03tbj30e80e8t93.jpg" }, "reposts_count": 0, "comments_count": 14, "attitudes_count": 1, "isLongText": false, "visible": { "type": 0, "list_id": 0 }, "mblogtype": 0, "bid": "FfvjxETA3", "pics": [ { "pid": "006apWvQgy1fi7fkqpatfj30j60j6jsg", "url": "https://wx1.sinaimg.cn/orj360/006apWvQgy1fi7fkqpatfj30j60j6jsg.jpg", "size": "orj360", "geo": { "width": 360, "height": 360, "croped": false }, "large": { "size": "large", "url": "https://wx1.sinaimg.cn/large/006apWvQgy1fi7fkqpatfj30j60j6jsg.jpg", "geo": { "width": "690", "height": "690", "croped": false } } }, { "pid": "006apWvQgy1fi7fkuj1tvg308c0fkmxy", "url": "https://wx1.sinaimg.cn/orj360/006apWvQgy1fi7fkuj1tvg308c0fkmxy.gif", "size": "orj360", "geo": { "width": "300", "height": "560", "croped": false }, "large": { "size": "large", "url": "https://wx1.sinaimg.cn/large/006apWvQgy1fi7fkuj1tvg308c0fkmxy.gif", "geo": { "width": "300", "height": "560", "croped": false } } } ] }, "show_type": 0, "openurl": "" }, { "card_type": 9, "itemid": "1076035650743478_-_4136663145262324", "scheme": "https://m.weibo.cn/status/FfnM6m4Yc?mblogid=FfnM6m4Yc&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "mblog": { "created_at": "08-03", "id": "4136663145262324", "mid": "4136663145262324", "idstr": "4136663145262324", "text": "輸入法，你們喜歡用哪種？<span class=\"url-icon\"><img src=\"//h5.sinaimg.cn/m/emoticon/icon/others/d_doge-d903433c82.png\" style=\"width:1em;height:1em;\" alt=\"[doge]\"></span> ", "textLength": 30, "source": "微博 weibo.com", "favorited": false, "thumbnail_pic": "http://wx4.sinaimg.cn/thumbnail/006apWvQgy1fi6i8tkspqj30ku0i7mz4.jpg", "bmiddle_pic": "http://wx4.sinaimg.cn/bmiddle/006apWvQgy1fi6i8tkspqj30ku0i7mz4.jpg", "original_pic": "http://wx4.sinaimg.cn/large/006apWvQgy1fi6i8tkspqj30ku0i7mz4.jpg", "user": { "id": 5650743478, "screen_name": "京東客服", "profile_image_url": "https://tva4.sinaimg.cn/crop.38.7.206.206.180/006apWvQjw8f9dwuejt68j307y0630sz.jpg", "profile_url": "https://m.weibo.cn/u/5650743478?uid=5650743478&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "statuses_count": 3245, "verified": true, "verified_type": 2, "verified_type_ext": 0, "verified_reason": "北京京東世紀貿易有限公司", "description": "訂單諮詢、問題反饋、意見建議……獲取專業貼心服務，盡在京東客服", "gender": "f", "mbtype": 2, "urank": 29, "mbrank": 2, "follow_me": false, "following": false, "followers_count": 18427, "follow_count": 235, "cover_image_phone": "https://tva4.sinaimg.cn/crop.0.0.640.640.640/006apWvQjw1f2g20q03tbj30e80e8t93.jpg" }, "reposts_count": 4, "comments_count": 40, "attitudes_count": 6, "isLongText": false, "visible": { "type": 0, "list_id": 0 }, "mblogtype": 0, "bid": "FfnM6m4Yc", "pics": [ { "pid": "006apWvQgy1fi6i8tkspqj30ku0i7mz4", "url": "https://wx4.sinaimg.cn/orj360/006apWvQgy1fi6i8tkspqj30ku0i7mz4.jpg", "size": "orj360", "geo": { "width": 309, "height": 270, "croped": false }, "large": { "size": "large", "url": "https://wx4.sinaimg.cn/large/006apWvQgy1fi6i8tkspqj30ku0i7mz4.jpg", "geo": { "width": "750", "height": "655", "croped": false } } }, { "pid": "006apWvQgy1fi6i8z010xj30ku0h6jte", "url": "https://wx3.sinaimg.cn/orj360/006apWvQgy1fi6i8z010xj30ku0h6jte.jpg", "size": "orj360", "geo": { "width": 327, "height": 270, "croped": false }, "large": { "size": "large", "url": "https://wx3.sinaimg.cn/large/006apWvQgy1fi6i8z010xj30ku0h6jte.jpg", "geo": { "width": "750", "height": "618", "croped": false } } }, { "pid": "006apWvQgy1fi6i988w7pj30kt0hbgms", "url": "https://wx2.sinaimg.cn/orj360/006apWvQgy1fi6i988w7pj30kt0hbgms.jpg", "size": "orj360", "geo": { "width": 324, "height": 270, "croped": false }, "large": { "size": "large", "url": "https://wx2.sinaimg.cn/large/006apWvQgy1fi6i988w7pj30kt0hbgms.jpg", "geo": { "width": "749", "height": "623", "croped": false } } }, { "pid": "006apWvQgy1fi6i9bnkgfj30ku0gwgmj", "url": "https://wx2.sinaimg.cn/orj360/006apWvQgy1fi6i9bnkgfj30ku0gwgmj.jpg", "size": "orj360", "geo": { "width": 333, "height": 270, "croped": false }, "large": { "size": "large", "url": "https://wx2.sinaimg.cn/large/006apWvQgy1fi6i9bnkgfj30ku0gwgmj.jpg", "geo": { "width": "750", "height": "608", "croped": false } } } ] }, "show_type": 0, "openurl": "" }, { "card_type": 9, "itemid": "1076035650743478_-_4136613988263792", "scheme": "https://m.weibo.cn/status/FfmuOyFMY?mblogid=FfmuOyFMY&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "mblog": { "created_at": "08-03", "id": "4136613988263792", "mid": "4136613988263792", "idstr": "4136613988263792", "text": "<a class='k' href='https://m.weibo.cn/k/%E5%BC%A0%E8%8B%A5%E6%98%80%E5%94%90%E8%89%BA%E6%98%95%E5%85%AC%E5%BC%80%E6%81%8B%E6%83%85?from=feed'>#張若昀唐藝昕公開戀情#</a> 恭喜呀<span class=\"url-icon\"><img src=\"//h5.sinaimg.cn/m/emoticon/icon/others/l_xin-8e9a1a0346.png\" style=\"width:1em;height:1em;\" alt=\"[心]\"></span><span class=\"url-icon\"><img src=\"//h5.sinaimg.cn/m/emoticon/icon/others/l_xin-8e9a1a0346.png\" style=\"width:1em;height:1em;\" alt=\"[心]\"></span><span class=\"url-icon\"><img src=\"//h5.sinaimg.cn/m/emoticon/icon/others/l_xin-8e9a1a0346.png\" style=\"width:1em;height:1em;\" alt=\"[心]\"></span>，大家就默默乾了這碗狗糧吧，狗糧夠吃嗎？不夠吃的話，你（jing）們（dong）懂（you）的（shou）<span class=\"url-icon\"><img src=\"//h5.sinaimg.cn/m/emoticon/icon/default/d_wabishi-f5765407f7.png\" style=\"width:1em;height:1em;\" alt=\"[挖鼻]\"></span>", "source": "微博 weibo.com", "favorited": false, "user": { "id": 5650743478, "screen_name": "京東客服", "profile_image_url": "https://tva4.sinaimg.cn/crop.38.7.206.206.180/006apWvQjw8f9dwuejt68j307y0630sz.jpg", "profile_url": "https://m.weibo.cn/u/5650743478?uid=5650743478&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "statuses_count": 3245, "verified": true, "verified_type": 2, "verified_type_ext": 0, "verified_reason": "北京京東世紀貿易有限公司", "description": "訂單諮詢、問題反饋、意見建議……獲取專業貼心服務，盡在京東客服", "gender": "f", "mbtype": 2, "urank": 29, "mbrank": 2, "follow_me": false, "following": false, "followers_count": 18427, "follow_count": 235, "cover_image_phone": "https://tva4.sinaimg.cn/crop.0.0.640.640.640/006apWvQjw1f2g20q03tbj30e80e8t93.jpg" }, "retweeted_status": { "created_at": "08-02", "id": "4136423907632073", "mid": "4136423907632073", "idstr": "4136423907632073", "text": "時光賜給我們盜不走的愛人，而你賜給我時光。<a href='https://m.weibo.cn/n/唐藝昕'>@唐藝昕</a> ", "textLength": 49, "source": "iPhone 6s", "favorited": false, "thumbnail_pic": "http://wx1.sinaimg.cn/thumbnail/6cf03c75ly1fi5qtg3z8fj20hs0nqq46.jpg", "bmiddle_pic": "http://wx1.sinaimg.cn/bmiddle/6cf03c75ly1fi5qtg3z8fj20hs0nqq46.jpg", "original_pic": "http://wx1.sinaimg.cn/large/6cf03c75ly1fi5qtg3z8fj20hs0nqq46.jpg", "user": { "id": 1827683445, "screen_name": "張若昀", "profile_image_url": "https://tva3.sinaimg.cn/crop.9.0.494.494.180/6cf03c75jw8fajncv51lvj20e80dq74i.jpg", "profile_url": "https://m.weibo.cn/u/1827683445?uid=1827683445&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "statuses_count": 1199, "verified": true, "verified_type": 0, "verified_type_ext": 1, "verified_reason": "演員張若昀", "description": "Per Aspera Ad Astra 循此苦旅，以達天際。 工作郵箱：[email protected]", "gender": "m", "mbtype": 12, "urank": 37, "mbrank": 6, "follow_me": false, "following": false, "followers_count": 13527839, "follow_count": 195, "cover_image_phone": "https://tva1.sinaimg.cn/crop.0.0.640.640.640/549d0121tw1egm1kjly3jj20hs0hsq4f.jpg" }, "picStatus": "0:1,1:1", "reposts_count": 283896, "comments_count": 325438, "attitudes_count": 2380726, "isLongText": false, "visible": { "type": 0, "list_id": 0 }, "cardid": "star_183", "bid": "Ffhyew1rX", "pics": [ { "pid": "6cf03c75ly1fi5qtg3z8fj20hs0nqq46", "url": "https://wx1.sinaimg.cn/orj360/6cf03c75ly1fi5qtg3z8fj20hs0nqq46.jpg", "size": "orj360", "geo": { "width": 360, "height": 480, "croped": false }, "large": { "size": "large", "url": "https://wx1.sinaimg.cn/large/6cf03c75ly1fi5qtg3z8fj20hs0nqq46.jpg", "geo": { "width": "640", "height": "854", "croped": false } } }, { "pid": "6cf03c75ly1fi5qtfv90rj20c80c6dgs", "url": "https://wx1.sinaimg.cn/orj360/6cf03c75ly1fi5qtfv90rj20c80c6dgs.jpg", "size": "orj360", "geo": { "width": 271, "height": 270, "croped": false }, "large": { "size": "large", "url": "https://wx1.sinaimg.cn/large/6cf03c75ly1fi5qtfv90rj20c80c6dgs.jpg", "geo": { "width": "440", "height": "438", "croped": false } } } ] }, "reposts_count": 3, "comments_count": 13, "attitudes_count": 6, "isLongText": false, "visible": { "type": 0, "list_id": 0 }, "mblogtype": 0, "raw_text": "#張若昀唐藝昕公開戀情# 恭喜呀[心][心][心]，大家就默默乾了這碗狗糧吧，狗糧夠吃嗎？不夠吃的話，你（jing）們（dong）懂（you）的（shou）[挖鼻]", "bid": "FfmuOyFMY" }, "show_type": 0, "openurl": "" }, { "card_type": 9, "itemid": "1076035650743478_-_4136598981629551", "scheme": "https://m.weibo.cn/status/Ffm6C6PV5?mblogid=Ffm6C6PV5&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "mblog": { "created_at": "08-03", "id": "4136598981629551", "mid": "4136598981629551", "idstr": "4136598981629551", "text": "彷彿看到了自己<span class=\"url-icon\"><img src=\"//h5.sinaimg.cn/m/emoticon/icon/others/d_erha-0d2bea3a7d.png\" style=\"width:1em;height:1em;\" alt=\"[二哈]\"></span>", "source": "微博 weibo.com", "favorited": false, "user": { "id": 5650743478, "screen_name": "京東客服", "profile_image_url": "https://tva4.sinaimg.cn/crop.38.7.206.206.180/006apWvQjw8f9dwuejt68j307y0630sz.jpg", "profile_url": "https://m.weibo.cn/u/5650743478?uid=5650743478&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "statuses_count": 3245, "verified": true, "verified_type": 2, "verified_type_ext": 0, "verified_reason": "北京京東世紀貿易有限公司", "description": "訂單諮詢、問題反饋、意見建議……獲取專業貼心服務，盡在京東客服", "gender": "f", "mbtype": 2, "urank": 29, "mbrank": 2, "follow_me": false, "following": false, "followers_count": 18427, "follow_count": 235, "cover_image_phone": "https://tva4.sinaimg.cn/crop.0.0.640.640.640/006apWvQjw1f2g20q03tbj30e80e8t93.jpg" }, "retweeted_status": { "created_at": "08-02", "id": "4136434165892638", "mid": "4136434165892638", "idstr": "4136434165892638", "text": "我在張若昀和唐藝昕公開戀情的微博裡看到了你唉～～<span class=\"url-icon\"><img src=\"//h5.sinaimg.cn/m/emoticon/icon/others/d_doge-d903433c82.png\" style=\"width:1em;height:1em;\" alt=\"[doge]\"></span> ", "textLength": 54, "source": "", "favorited": false, "thumbnail_pic": "http://wx3.sinaimg.cn/thumbnail/bb97de37ly1fi5s0g76jrj20yi0p1n0m.jpg", "bmiddle_pic": "http://wx3.sinaimg.cn/bmiddle/bb97de37ly1fi5s0g76jrj20yi0p1n0m.jpg", "original_pic": "http://wx3.sinaimg.cn/large/bb97de37ly1fi5s0g76jrj20yi0p1n0m.jpg", "user": { "id": 3147292215, "screen_name": "草圖君", "profile_image_url": "https://tva4.sinaimg.cn/crop.0.0.511.511.180/bb97de37jw8f57ewfuqt9j20e70e8q37.jpg", "profile_url": "https://m.weibo.cn/u/3147292215?uid=3147292215&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "statuses_count": 5980, "verified": true, "verified_type": 0, "verified_type_ext": 1, "verified_reason": "直播紅人 微博知名綜藝博主", "description": "一個得罪了半個娛樂圈的少年", "gender": "m", "mbtype": 12, "urank": 44, "mbrank": 6, "follow_me": false, "following": false, "followers_count": 6192418, "follow_count": 433, "cover_image_phone": "https://tva2.sinaimg.cn/crop.0.0.640.640.640/bb97de37jw1ewysfmiioyj20yi0ykqe7.jpg" }, "picStatus": "0:1,1:1,2:1,3:1", "reposts_count": 3832, "comments_count": 7349, "attitudes_count": 65785, "isLongText": false, "visible": { "type": 0, "list_id": 0 }, "bid": "FfhOMoIWy", "pics": [ { "pid": "bb97de37ly1fi5s0g76jrj20yi0p1n0m", "url": "https://wx3.sinaimg.cn/orj360/bb97de37ly1fi5s0g76jrj20yi0p1n0m.jpg", "size": "orj360", "geo": { "width": 372, "height": 270, "croped": false }, "large": { "size": "large", "url": "https://wx3.sinaimg.cn/large/bb97de37ly1fi5s0g76jrj20yi0p1n0m.jpg", "geo": { "width": "1242", "height": "901", "croped": false } } }, { "pid": "bb97de37ly1fi5s0goz0nj20hs0nq0tw", "url": "https://wx4.sinaimg.cn/orj360/bb97de37ly1fi5s0goz0nj20hs0nq0tw.jpg", "size": "orj360", "geo": { "width": 360, "height": 480, "croped": false }, "large": { "size": "large", "url": "https://wx4.sinaimg.cn/large/bb97de37ly1fi5s0goz0nj20hs0nq0tw.jpg", "geo": { "width": "640", "height": "854", "croped": false } } }, { "pid": "bb97de37ly1fi5s0h69g3j20c80c7juk", "url": "https://wx1.sinaimg.cn/orj360/bb97de37ly1fi5s0h69g3j20c80c7juk.jpg", "size": "orj360", "geo": { "width": 270, "height": 270, "croped": false }, "large": { "size": "large", "url": "https://wx1.sinaimg.cn/large/bb97de37ly1fi5s0h69g3j20c80c7juk.jpg", "geo": { "width": "440", "height": "439", "croped": false } } }, { "pid": "bb97de37ly1fi5s0fg68mj202g02g3yo", "url": "https://wx1.sinaimg.cn/orj360/bb97de37ly1fi5s0fg68mj202g02g3yo.jpg", "size": "orj360", "geo": { "width": "88", "height": "88", "croped": false }, "large": { "size": "large", "url": "https://wx1.sinaimg.cn/large/bb97de37ly1fi5s0fg68mj202g02g3yo.jpg", "geo": { "width": "88", "height": "88", "croped": false } } } ] }, "reposts_count": 2, "comments_count": 21, "attitudes_count": 7, "isLongText": false, "visible": { "type": 0, "list_id": 0 }, "mblogtype": 0, "raw_text": "彷彿看到了自己[二哈]", "bid": "Ffm6C6PV5" }, "show_type": 0, "openurl": "" }, { "card_type": 11, "show_type": 0, "card_group": [], "openurl": "" }, { "card_type": 9, "itemid": "1076035650743478_-_4136407577953610", "scheme": "https://m.weibo.cn/status/Ffh7Txn62?mblogid=Ffh7Txn62&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "mblog": { "created_at": "08-02", "id": "4136407577953610", "mid": "4136407577953610", "idstr": "4136407577953610", "text": "<a class='k' href='https://m.weibo.cn/k/%E4%B8%80%E4%B8%AA%E6%84%9F%E4%BA%BA%E7%9A%84%E6%95%85%E4%BA%8B?from=feed'>#一個感人的故事#</a>去年暑假，8歲的小明特意坐了三個多小時車去奶奶家；奶奶為了小明也願意去縣城的超市買小明愛的薯片和巧克力等零食，但是奶奶家沒有WiFi和智慧手機，奶奶可以陪他一起看古裝電視劇；講他最愛聽的神話故事，唱小曲哄他睡覺……奶奶家有吃不完的零食，也不會"太無聊了"<br/>今年，奶奶提前做 ...<a href=\"/status/4136407577953610\">全文</a>", "textLength": 393, "source": "微博 weibo.com", "favorited": false, "user": { "id": 5650743478, "screen_name": "京東客服", "profile_image_url": "https://tva4.sinaimg.cn/crop.38.7.206.206.180/006apWvQjw8f9dwuejt68j307y0630sz.jpg", "profile_url": "https://m.weibo.cn/u/5650743478?uid=5650743478&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "statuses_count": 3245, "verified": true, "verified_type": 2, "verified_type_ext": 0, "verified_reason": "北京京東世紀貿易有限公司", "description": "訂單諮詢、問題反饋、意見建議……獲取專業貼心服務，盡在京東客服", "gender": "f", "mbtype": 2, "urank": 29, "mbrank": 2, "follow_me": false, "following": false, "followers_count": 18427, "follow_count": 235, "cover_image_phone": "https://tva4.sinaimg.cn/crop.0.0.640.640.640/006apWvQjw1f2g20q03tbj30e80e8t93.jpg" }, "reposts_count": 6, "comments_count": 17, "attitudes_count": 2, "isLongText": true, "visible": { "type": 0, "list_id": 0 }, "mblogtype": 0, "page_info": { "page_pic": { "url": "https://ww3.sinaimg.cn/thumb180/74f67c55jw9ey0hrixq57j2050050t92.jpg" }, "page_url": "https://m.weibo.cn/p/index?containerid=100808f50fb5741ffd610570b92baf2cc3b342&extparam=%E4%B8%80%E4%B8%AA%E6%84%9F%E4%BA%BA%E7%9A%84%E6%95%85%E4%BA%8B&luicode=10000011&lfid=1076035650743478&featurecode=20000320", "page_title": "#一個感人的故事#", "content1": "", "content2": "3人關注", "type": "topic" }, "bid": "Ffh7Txn62" }, "show_type": 0, "openurl": "" } ], "ok": 1, "showAppTips": 0, "scheme": "sinaweibo://cardlist?containerid=1076035650743478&luicode=10000011&lfid=100103type=1&q=京東客服&featurecode=20000320" }
###上面只是一個頁面的說說，估計寫前端移動端的要暈死，好惡心，要是返回個null或者空回來。。
上面程式碼可以直接在jsonview裡面進行格式化，
爬取的欄位是：cards 下面的mblog下面的：text ，idstr(拼接評論頁的)
這裡的id就是idstr
詳情頁就是上面評論條目的json串，搞下來也是一大把，跟上面的差不多，詳情頁裡面的資料跟評論頁的資料差不多，這裡就不再繼續多些了，因為上面的內容已經佔用的差不多了
因為微博的封IP地址的原因，所以第一次爬取了4w多資料，就GG了，第二天晚上睡眠30秒，爬取一條，發現，毛用也沒有，只好是接著爬，ip不封了之後換了cookie，換了starturl，換了page索引繼續爬取，也睡眠了10秒，反正睡多了也沒用，最後爬取的垃圾資料有22萬左右吧，去掉去重不要的估計也就4000不知道有沒有，反正也沒數。
附上幾張爬蟲過程中的圖片截圖：
最後是微博資料的結果圖片：
這裡的程式碼上傳到github上了，有需要的話可以自己去下載，另外寫了一份類似於 爬取新浪微博京東客服 @京東客服的簡單爬蟲。
發一下牢騷，json串又多又大又不穩定，返回不一致
貼上部分程式碼：
# encoding=utf8
import requests
import json
import re
import time
startUrl = 'https://m.weibo.cn/api/container/getIndex?uid=5650743478&luicode=10000011&lfid=100103type%3D1%26q%3D%E4%BA%AC%E4%B8%9C%E5%AE%A2%E6%9C%8D&featurecode=20000320&type=uid&value=5650743478&containerid=1076035650743478'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:54.0) Gecko/20100101 Firefox/54.0'
,
'Cookie': 'ALF=1504709445; SCF=Ag0epa_4tyFCglnCwHJiaRDznUy645wpqEhg-dG3Sv0cbfGX1wNmqXPnHQroard1FW2nn3RdCnmux4VZ7bFRuMo.; SUHB=0ebt4qVvtKU1d7; _T_WM=22bb4d80315608a0e9bd3bf92b3c1dac; SUB=_2A250jA4VDeRhGeBN6FsT8i7MyTyIHXVXjpJdrDV6PUJbktBeLXjBkW1oTOqmqg0rff3UmekP4TzhMFYtsw..; SUBP=0033WrSXqPxfM725Ws9jqgMF55529P9D9WFNrBkhSeVrfPGckwnaFCcy5JpX5o2p5NHD95Qce0e4eoz7ehz7Ws4DqcjBIcHVdr.peoepeoefeK5Ee5tt; M_WEIBOCN_PARAMS=luicode%3D10000011%26lfid%3D100103type%253D1%2526q%253D%2540%25E4%25BA%25AC%25E4%25B8%259C%25E5%25AE%25A2%25E6%259C%258D%26featurecode%3D20000320%26fid%3D1076035650743478%26uicode%3D10000011'
,
'Host':'m.weibo.cn'
,
'Accept':'application/json, text/plain, */*',
'Accept-Language':'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3',
'Accept-Encoding':'gzip, deflate, br',
'X-Requested-With':'XMLHttpRequest',
'Referer':'https://m.weibo.cn/u/5650743478?uid=5650743478&luicode=10000011&lfid=100103type%3D1%26q%3D%40%E4%BA%AC%E4%B8%9C%E5%AE%A2%E6%9C%8D&featurecode=20000320',
}
# 詳情頁list
detaiList = []
# 說說
textList = []
# 說說跟詳情頁
textAnddetailList = []
# 評論數，詳情頁返回的是每一頁10個
commentsList = []
numSizeList = []
detaiLinks = []
def getJsonData(url):
req = requests.get(url, headers=headers)
# print(req.text)
return req.text
jsonData = getJsonData(startUrl)
def parseDetailListdata(listdata):
for detailData in listdata:
text = detailData['text'] if 'text' in detailData else ""
reply_text = detailData['reply_text'] if 'reply_text' in detailData else ""
f.write(text+'\r\n')
print(text)
print(reply_text)
f.write(reply_text + '\r\n')
# pass
def parseJsonData(jsonData):
global pagedetail
jsondata = json.loads(jsonData, 'utf-8')
print(jsondata)
listdata = jsondata['cards']if 'cards' in jsondata else ""
print(listdata)
for datainfo in listdata:
# print(datainfo)
mblog = datainfo['mblog'] if 'mblog' in datainfo else ""
# print(mblog)
if len(mblog)> 0 : # 有資料，繼續執行
descText = mblog['text']
# print(descText)
descText = getTextInfo(descText)
dex = '發表的說說開始：\r\n'
f.write(dex)
dex2 = '發表的說說內容：'+descText+'\r\n'
f.write(dex2)
print("發表的說說開始：")
print('發表的說說內容：'+descText)
textList.append(descText)
comments = mblog['comments_count'] # 評論數
numSizeList.append(comments)
# print(comments)
# if comments > 1: # 有評論，獲取到評論連結上的資料
# detailLine = datainfo['scheme']
# print(detailLine)
# detaiList.append(detailLine)
idstr = mblog['idstr']
detaiLinks = getpageSize(comments,idstr)
pagedetail = 1
for detaillink in detaiLinks:
jsonData2 = getJsonData(detaillink)
str11 = '評論詳情頁條目：'+str(pagedetail)+' .......\r\n'
f.write(str11)
print('評論詳情頁條目：'+str(pagedetail)+' .......')
print(jsonData2)
pagedetail = pagedetail +1
jsonDatadetail = json.loads(jsonData2, 'utf-8')
listdata = jsonDatadetail['data'] if 'data' in jsonDatadetail else ''
# print(listdata)
parseDetailListdata(listdata)
pagedetail = 1
print('主頁條目結束...')
f.write('主頁條目結束...\r\n')
# detailJsonStr = 'https://m.weibo.cn/api/comments/show?id=' + str(idstr) + '&page=' + str(comments)
# print(detailJsonStr)
# commentsList.append(detailJsonStr)
else:
# 在裡面的話，直接跳出方法
return
print('爬取結束......')
def getTextInfo(textStr):
# 得到文字內容
# for textStr in textList:
# print('***********')
regx = '<span(.*?)</span>'
strregx = re.compile(regx)
strregx = re.findall(strregx, str(textStr))
replacestr = str(textStr).replace('<span' + ''.join(strregx) + '</span>', '')
str1 = '<span'
sstr1 = str(textStr)[0:str(textStr).find(str1)]
# print(sstr1)
return sstr1
# print(textStr)
# print(replacestr)
# 得到文字詳情頁連結
def getpageSize(comments,idstr):
for i in range(1,int((comments / 10))+2):
# 評論也的link
detaiLink = 'https://m.weibo.cn/api/comments/show?id=' + str(idstr) + '&page=' +str(i)
detaiLinks.append(detaiLink)
# print(detaiLink)
return detaiLinks
# parseJsonData(jsonData)
# print(str(textList)) page = 7
# print(str(detaiList))
f = open('微博京東說說跟評論.txt', 'a',encoding='utf-8')
def main_start():
for inde in range(11,50):
# startUrl = 'https://m.weibo.cn/api/container/getIndex?uid=5650743478&luicode=10000011&lfid=100103type%3D1%26q%3D%E4%BA%AC%E4%B8%9C%E5%AE%A2%E6%9C%8D&featurecode=20000320&type=uid&value=5650743478&containerid=1005055650743478&page='+str(inde)
startUrl = 'https://m.weibo.cn/api/container/getIndex?uid=5650743478&luicode=10000011&lfid=100103type%3D1%26q%[email protected]%E4%BA%AC%E4%B8%9C%E5%AE%A2%E6%9C%8D&featurecode=20000320&type=uid&value=5650743478&containerid=1076035650743478&page={}'+str(inde)
pageindex = '頁數：'+str(inde)+'\r\n'
print('startUrl '+'index '+str(inde)+' '+startUrl)
f.write(pageindex)
data = getJsonData(startUrl)
parseJsonData(data)
time.sleep(2)
f.close()
main_start()
現在暫時可以借用這份程式碼，裡面的url跟cookie換一下，用自己的賬號就可以。另外爬蟲要學會用fiddler等類似的抓包工具，感覺確實是抓包利器。
公司996啊， 加上自己的能力有限，確實現在學習也就到這深度了 以後要多瞭解一下cookie池，代理池之類似的東西。
end