Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- import re
- import requests
- import sys
- ARCHIVE_URL = 'http://salery.livejournal.com/calendar'
- ARCHIVE_RE = (
- '<tr><td class="caption">Years</td></tr><tr>\n'
- '<td colspan="2" bgcolor="#ffffff">([\s\S]+?)</td>'
- )
- YEAR_RE = 'href="([^"]+)'
- DATE_RE = '<div align="center"><a href="([^"]+)'
- POST_RE = '<a href="([^#]+)#\w+" class="ljcut-link-expand" title="Read more..." >Read more...</a>'
- def getArchiveLinks():
- content = requests.get(ARCHIVE_URL).text
- match = re.search(ARCHIVE_RE, content)
- links = re.findall(YEAR_RE, match.group(1))
- return links
- def getArchiveLinksByYear(link):
- content = requests.get(link).text
- links = re.findall(DATE_RE, content)
- return links
- def getLinksByDate(link):
- content = requests.get(link).text
- links = re.findall(POST_RE, content)
- return links
- def main(args):
- links = []
- for x in getArchiveLinks():
- print(x)
- for x1 in getArchiveLinksByYear(x):
- print(x1)
- links += getLinksByDate(x1)
- print(links[-1])
- with open('links.txt', 'w') as f:
- f.write('\n'.join(links))
- return 0
- if __name__ == '__main__':
- sys.exit(main(sys.argv))
- """
- http://salery.livejournal.com/339.html
- http://salery.livejournal.com/767.html
- http://salery.livejournal.com/947.html
- http://salery.livejournal.com/1097.html
- http://salery.livejournal.com/1729.html
- http://salery.livejournal.com/1868.html
- http://salery.livejournal.com/2303.html
- http://salery.livejournal.com/2474.html
- http://salery.livejournal.com/2668.html
- http://salery.livejournal.com/2977.html
- http://salery.livejournal.com/3274.html
- http://salery.livejournal.com/3338.html
- http://salery.livejournal.com/3788.html
- http://salery.livejournal.com/3889.html
- http://salery.livejournal.com/4259.html
- http://salery.livejournal.com/4427.html
- http://salery.livejournal.com/4807.html
- http://salery.livejournal.com/5109.html
- http://salery.livejournal.com/5364.html
- http://salery.livejournal.com/5535.html
- http://salery.livejournal.com/5803.html
- http://salery.livejournal.com/6323.html
- http://salery.livejournal.com/6640.html
- http://salery.livejournal.com/6669.html
- http://salery.livejournal.com/6976.html
- http://salery.livejournal.com/7468.html
- http://salery.livejournal.com/7839.html
- http://salery.livejournal.com/8190.html
- http://salery.livejournal.com/8409.html
- http://salery.livejournal.com/8636.html
- http://salery.livejournal.com/8875.html
- http://salery.livejournal.com/9147.html
- http://salery.livejournal.com/9346.html
- http://salery.livejournal.com/9631.html
- http://salery.livejournal.com/10691.html
- http://salery.livejournal.com/10773.html
- http://salery.livejournal.com/11173.html
- http://salery.livejournal.com/11480.html
- http://salery.livejournal.com/11633.html
- http://salery.livejournal.com/11810.html
- http://salery.livejournal.com/12188.html
- http://salery.livejournal.com/12511.html
- http://salery.livejournal.com/12722.html
- http://salery.livejournal.com/12990.html
- http://salery.livejournal.com/13059.html
- http://salery.livejournal.com/13685.html
- http://salery.livejournal.com/13888.html
- http://salery.livejournal.com/14309.html
- http://salery.livejournal.com/14574.html
- http://salery.livejournal.com/14746.html
- http://salery.livejournal.com/14922.html
- http://salery.livejournal.com/15281.html
- http://salery.livejournal.com/16156.html
- http://salery.livejournal.com/16456.html
- http://salery.livejournal.com/16697.html
- http://salery.livejournal.com/17111.html
- http://salery.livejournal.com/17343.html
- http://salery.livejournal.com/17513.html
- http://salery.livejournal.com/17684.html
- http://salery.livejournal.com/18140.html
- http://salery.livejournal.com/18383.html
- http://salery.livejournal.com/18586.html
- http://salery.livejournal.com/19135.html
- http://salery.livejournal.com/19211.html
- http://salery.livejournal.com/19590.html
- http://salery.livejournal.com/19781.html
- http://salery.livejournal.com/20098.html
- http://salery.livejournal.com/20291.html
- http://salery.livejournal.com/20573.html
- http://salery.livejournal.com/20865.html
- http://salery.livejournal.com/21189.html
- http://salery.livejournal.com/21429.html
- http://salery.livejournal.com/22006.html
- http://salery.livejournal.com/22156.html
- http://salery.livejournal.com/22518.html
- http://salery.livejournal.com/22766.html
- http://salery.livejournal.com/23949.html
- http://salery.livejournal.com/24287.html
- http://salery.livejournal.com/24534.html
- http://salery.livejournal.com/24766.html
- http://salery.livejournal.com/24922.html
- http://salery.livejournal.com/25241.html
- http://salery.livejournal.com/25541.html
- http://salery.livejournal.com/25767.html
- http://salery.livejournal.com/26012.html
- http://salery.livejournal.com/26593.html
- http://salery.livejournal.com/26638.html
- http://salery.livejournal.com/27058.html
- http://salery.livejournal.com/27201.html
- http://salery.livejournal.com/27615.html
- http://salery.livejournal.com/28316.html
- http://salery.livejournal.com/28747.html
- http://salery.livejournal.com/29089.html
- http://salery.livejournal.com/29412.html
- http://salery.livejournal.com/29608.html
- http://salery.livejournal.com/29951.html
- http://salery.livejournal.com/30650.html
- http://salery.livejournal.com/30938.html
- http://salery.livejournal.com/31151.html
- http://salery.livejournal.com/31623.html
- http://salery.livejournal.com/31898.html
- http://salery.livejournal.com/32146.html
- http://salery.livejournal.com/32452.html
- http://salery.livejournal.com/32918.html
- http://salery.livejournal.com/33113.html
- http://salery.livejournal.com/33295.html
- http://salery.livejournal.com/33542.html
- http://salery.livejournal.com/34420.html
- http://salery.livejournal.com/34564.html
- http://salery.livejournal.com/35237.html
- http://salery.livejournal.com/35394.html
- http://salery.livejournal.com/35789.html
- http://salery.livejournal.com/36002.html
- http://salery.livejournal.com/36223.html
- http://salery.livejournal.com/36494.html
- http://salery.livejournal.com/36654.html
- http://salery.livejournal.com/36957.html
- http://salery.livejournal.com/37228.html
- http://salery.livejournal.com/37556.html
- http://salery.livejournal.com/37822.html
- http://salery.livejournal.com/38227.html
- http://salery.livejournal.com/38792.html
- http://salery.livejournal.com/39160.html
- http://salery.livejournal.com/40132.html
- http://salery.livejournal.com/40637.html
- http://salery.livejournal.com/40855.html
- http://salery.livejournal.com/41039.html
- http://salery.livejournal.com/41230.html
- http://salery.livejournal.com/41894.html
- http://salery.livejournal.com/42122.html
- http://salery.livejournal.com/42694.html
- http://salery.livejournal.com/42785.html
- http://salery.livejournal.com/43134.html
- http://salery.livejournal.com/44022.html
- http://salery.livejournal.com/44112.html
- http://salery.livejournal.com/44297.html
- http://salery.livejournal.com/44580.html
- http://salery.livejournal.com/44819.html
- http://salery.livejournal.com/45188.html
- http://salery.livejournal.com/45523.html
- http://salery.livejournal.com/45675.html
- http://salery.livejournal.com/45835.html
- http://salery.livejournal.com/46310.html
- http://salery.livejournal.com/46614.html
- http://salery.livejournal.com/47417.html
- http://salery.livejournal.com/47752.html
- http://salery.livejournal.com/47937.html
- http://salery.livejournal.com/48220.html
- http://salery.livejournal.com/48443.html
- http://salery.livejournal.com/49350.html
- http://salery.livejournal.com/49641.html
- http://salery.livejournal.com/49727.html
- http://salery.livejournal.com/50067.html
- http://salery.livejournal.com/51013.html
- http://salery.livejournal.com/53135.html
- http://salery.livejournal.com/53331.html
- http://salery.livejournal.com/54418.html
- http://salery.livejournal.com/54553.html
- http://salery.livejournal.com/55079.html
- http://salery.livejournal.com/55361.html
- http://salery.livejournal.com/56657.html
- http://salery.livejournal.com/57068.html
- http://salery.livejournal.com/58992.html
- http://salery.livejournal.com/60081.html
- http://salery.livejournal.com/60824.html
- http://salery.livejournal.com/61029.html
- http://salery.livejournal.com/61551.html
- http://salery.livejournal.com/61937.html
- http://salery.livejournal.com/62387.html
- http://salery.livejournal.com/62486.html
- http://salery.livejournal.com/62954.html
- http://salery.livejournal.com/63203.html
- http://salery.livejournal.com/63523.html
- http://salery.livejournal.com/64415.html
- http://salery.livejournal.com/64761.html
- http://genrogge.ru/hwj/" target="_blank" title="Полное издание, №№ 1–84. Свыше 1 500 фотографий и иллюстраций. 1699 страниц, включая оглавления и отдельные наградные списки в распознанном тексте" rel="nofollow">«Летопись войны с Японией»</a> и <a href="http://genrogge.ru/wwi-1914-1917/" target="_blank" title="Полное издание, №№ 1–132. Свыше 2 000 фотографий и иллюстраций. 2300 страниц, включая сообщения Официального отдела." rel="nofollow">«Летопись войны 1914–15–16–17 гг.»</a> — с тысячами фотографий).<br /></p><p>Собственно, чтобы представить страну, достаточно посмотреть на лица. Помню, в 80-х на Петровских Линиях кто-то устроил фотовыставку (приуроченную к Первой мировой). Всего-то две комнатки, но она пользовалась огромной популярностью. Это был культурный шок: сразу несколько сот «старых» лиц под звуки маршей и вальсов того времени. Как жаль, что никто до сих пор не додумался переиздать (хотя бы в более скромном виде) что-нибудь из альбомов, издававшихся в России в начале ХХ в. Я вынужден был ограничиться изучаемым контингентом, но вообще-то там много всего - от польских помещиков до аксакалов среднеазиатского местного управления (очень интересны, кстати, многочисленные портреты предпринимателей средней руки). <br /></p><p>Довольно любопытны фото одних и тех же лиц в разном возрасте. Кто-то из писателей (кажется, Акунин) даже призвал на сайте присылать ему такие на конкурс. Делать из этого какой-то «конкурс», конечно, пошлость, но сама идея очень неплоха. Старых (дорев.) фото такого рода, правда, мало, но встречаются. Мне тоже попадались. Вот, например (тут даже люди специально сфотографировались в тех же самых позах), между фото — 12 лет и примерно столько же тыс. км.</p><b data-widget='ljcut' data-widget-options='{"sticky":false,"cutid":1,"journalid":"11178575","placeholders":0,"ditemid":64905}' class="ljcut-link lj-widget"><span class='ljcut-brace'>( </span><span class="ljcut-decor"><a href="http://salery.livejournal.com/64905.html
- http://salery.livejournal.com/65421.html
- http://salery.livejournal.com/65584.html
- http://salery.livejournal.com/65970.html
- http://salery.livejournal.com/66238.html
- http://salery.livejournal.com/66585.html
- http://salery.livejournal.com/67227.html
- http://salery.livejournal.com/67498.html
- http://salery.livejournal.com/67777.html
- http://salery.livejournal.com/68479.html
- http://salery.livejournal.com/68782.html
- http://salery.livejournal.com/69668.html
- http://salery.livejournal.com/69963.html
- http://salery.livejournal.com/70719.html
- http://salery.livejournal.com/71271.html
- http://salery.livejournal.com/71556.html
- http://salery.livejournal.com/71746.html
- http://salery.livejournal.com/72482.html
- http://salery.livejournal.com/72839.html
- http://salery.livejournal.com/73036.html
- http://salery.livejournal.com/73460.html
- http://salery.livejournal.com/73627.html
- http://salery.livejournal.com/74487.html
- http://salery.livejournal.com/74580.html
- http://salery.livejournal.com/74922.html
- http://salery.livejournal.com/75231.html
- http://salery.livejournal.com/75771.html
- http://salery.livejournal.com/75929.html
- http://salery.livejournal.com/76440.html
- http://salery.livejournal.com/76662.html
- http://salery.livejournal.com/77235.html
- http://salery.livejournal.com/77500.html
- http://salery.livejournal.com/77600.html
- http://salery.livejournal.com/78299.html
- http://salery.livejournal.com/78586.html
- http://salery.livejournal.com/78760.html
- http://salery.livejournal.com/79051.html
- http://salery.livejournal.com/79866.html
- http://salery.livejournal.com/80702.html
- http://salery.livejournal.com/80946.html
- http://salery.livejournal.com/81205.html
- http://salery.livejournal.com/81456.html
- http://salery.livejournal.com/81892.html
- http://salery.livejournal.com/81986.html
- http://salery.livejournal.com/82176.html
- http://salery.livejournal.com/82570.html
- http://salery.livejournal.com/83748.html
- http://salery.livejournal.com/84191.html
- http://salery.livejournal.com/84252.html
- http://salery.livejournal.com/85175.html
- http://salery.livejournal.com/85391.html
- http://salery.livejournal.com/86335.html
- http://salery.livejournal.com/86840.html
- http://salery.livejournal.com/87078.html
- http://salery.livejournal.com/87375.html
- http://salery.livejournal.com/87663.html
- http://salery.livejournal.com/88140.html
- http://salery.livejournal.com/88334.html
- http://salery.livejournal.com/88788.html
- http://salery.livejournal.com/89048.html
- http://salery.livejournal.com/89497.html
- http://salery.livejournal.com/89707.html
- http://salery.livejournal.com/90074.html
- http://salery.livejournal.com/90243.html
- http://salery.livejournal.com/90532.html
- http://salery.livejournal.com/90810.html
- http://salery.livejournal.com/90921.html
- http://salery.livejournal.com/91218.html
- http://salery.livejournal.com/91641.html
- http://salery.livejournal.com/91678.html
- http://salery.livejournal.com/91927.html
- http://salery.livejournal.com/92274.html
- http://salery.livejournal.com/92433.html
- http://salery.livejournal.com/92810.html
- http://salery.livejournal.com/93105.html
- http://salery.livejournal.com/93223.html
- http://salery.livejournal.com/93444.html
- http://salery.livejournal.com/93865.html
- http://salery.livejournal.com/94036.html
- http://salery.livejournal.com/94222.html
- http://salery.livejournal.com/94557.html
- http://salery.livejournal.com/94778.html
- http://salery.livejournal.com/95105.html
- http://salery.livejournal.com/95351.html
- http://salery.livejournal.com/95567.html
- http://salery.livejournal.com/95797.html
- http://salery.livejournal.com/96009.html
- http://salery.livejournal.com/96424.html
- http://salery.livejournal.com/96727.html
- http://salery.livejournal.com/96802.html
- http://salery.livejournal.com/97198.html
- http://salery.livejournal.com/97711.html
- http://salery.livejournal.com/98284.html
- http://salery.livejournal.com/98381.html
- http://salery.livejournal.com/98751.html
- http://salery.livejournal.com/99020.html
- http://salery.livejournal.com/99179.html
- http://salery.livejournal.com/99480.html
- http://salery.livejournal.com/99663.html
- http://salery.livejournal.com/99852.html
- http://salery.livejournal.com/100515.html
- http://salery.livejournal.com/100709.html
- http://salery.livejournal.com/101451.html
- http://salery.livejournal.com/101662.html
- http://salery.livejournal.com/101938.html
- http://salery.livejournal.com/102303.html
- http://salery.livejournal.com/102512.html
- http://salery.livejournal.com/102682.html
- http://salery.livejournal.com/102996.html
- http://salery.livejournal.com/103418.html
- http://salery.livejournal.com/103530.html
- http://salery.livejournal.com/103761.html
- http://salery.livejournal.com/103967.html
- http://salery.livejournal.com/104255.html
- http://salery.livejournal.com/104465.html
- http://salery.livejournal.com/104750.html
- http://salery.livejournal.com/105086.html
- http://salery.livejournal.com/105718.html
- http://salery.livejournal.com/105855.html
- http://salery.livejournal.com/106206.html
- http://salery.livejournal.com/106460.html
- http://salery.livejournal.com/106635.html
- http://salery.livejournal.com/106753.html
- http://salery.livejournal.com/107114.html
- http://salery.livejournal.com/107401.html
- http://salery.livejournal.com/107655.html
- http://salery.livejournal.com/108371.html
- http://salery.livejournal.com/108754.html
- http://salery.livejournal.com/109000.html
- http://salery.livejournal.com/109179.html
- http://salery.livejournal.com/109414.html
- http://salery.livejournal.com/109658.html
- http://salery.livejournal.com/109970.html
- http://salery.livejournal.com/110321.html
- http://salery.livejournal.com/110817.html
- http://salery.livejournal.com/110980.html
- http://salery.livejournal.com/111449.html
- http://salery.livejournal.com/112181.html
- http://salery.livejournal.com/112453.html
- http://salery.livejournal.com/112706.html
- http://salery.livejournal.com/113100.html
- http://salery.livejournal.com/113265.html
- http://salery.livejournal.com/113509.html
- http://salery.livejournal.com/113714.html
- http://salery.livejournal.com/113952.html
- http://salery.livejournal.com/114295.html
- http://salery.livejournal.com/114484.html
- http://salery.livejournal.com/114702.html
- http://salery.livejournal.com/115102.html
- http://salery.livejournal.com/115445.html
- http://salery.livejournal.com/115479.html
- http://salery.livejournal.com/116186.html
- http://salery.livejournal.com/116260.html
- http://salery.livejournal.com/116483.html
- http://salery.livejournal.com/116852.html
- http://salery.livejournal.com/117190.html
- http://salery.livejournal.com/117370.html
- http://salery.livejournal.com/117519.html
- http://salery.livejournal.com/117984.html
- http://salery.livejournal.com/118149.html
- http://salery.livejournal.com/118757.html
- http://salery.livejournal.com/118981.html
- http://salery.livejournal.com/119040.html
- http://salery.livejournal.com/119320.html
- http://salery.livejournal.com/119573.html
- http://salery.livejournal.com/119923.html
- http://salery.livejournal.com/120242.html
- http://salery.livejournal.com/120480.html
- http://salery.livejournal.com/120622.html
- http://salery.livejournal.com/121006.html
- http://salery.livejournal.com/121709.html
- http://salery.livejournal.com/122345.html
- http://salery.livejournal.com/122434.html
- http://salery.livejournal.com/123062.html
- http://salery.livejournal.com/123443.html
- http://salery.livejournal.com/123826.html
- http://salery.livejournal.com/124098.html
- http://salery.livejournal.com/124427.html
- http://salery.livejournal.com/124738.html
- http://salery.livejournal.com/125148.html
- http://salery.livejournal.com/125335.html
- http://salery.livejournal.com/125653.html
- http://salery.livejournal.com/125784.html
- http://salery.livejournal.com/126114.html
- http://salery.livejournal.com/126808.html
- http://salery.livejournal.com/127106.html
- http://salery.livejournal.com/127570.html
- http://salery.livejournal.com/127825.html
- http://salery.livejournal.com/128175.html
- http://salery.livejournal.com/128642.html
- http://salery.livejournal.com/128917.html
- http://salery.livejournal.com/129223.html
- http://salery.livejournal.com/129372.html
- http://salery.livejournal.com/129539.html
- """
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement