Created
March 8, 2020 14:23
-
-
Save 0x48piraj/b982d465cbc4e0521fc1afd2d9250af7 to your computer and use it in GitHub Desktop.
Extracting Gizmodo journalists in #cybersecurity
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# https://gizmodo.com/tag/cybersecurity?startIndex=20 | |
import requests | |
import re | |
lst=[] | |
for qr in range(20,481,20): # 480 | |
r = requests.get("https://gizmodo.com/tag/cybersecurity?startIndex=" + str(qr)) | |
for i in list(set(re.findall(r'(?<=kinja.com/)[^"]*', str(r.content)))): | |
if ""," in i: | |
lst.append(i.split("",")[0]) | |
for q in range (481, 495): | |
r = requests.get("https://gizmodo.com/tag/cybersecurity?startIndex=" + str(q)) | |
for i in list(set(re.findall(r'(?<=kinja.com/)[^"]*', str(r.content)))): | |
if ""," in i: | |
print(i.split("",")[0]) | |
lst.append(i.split("",")[0]) | |
writers = list(set(lst)) | |
# writers = ['jack-loftus-old', 'caseychan', 'kylenw', 'liptakaa', 'rosa', 'chengela', 'mattnovak', 'seanhollister', 'sidneyfussell', 'maddiestone', 'ajdellinger', 'andrewcouts', 'sambiddle', 'catiekeck', 'laurendavis', 'kevin-lee-old', 'tjenningsbrown', 'darrenorf', 'alejandroalba', 'chris-mills', 'dan-nosowitz-old', 'fruitsoftheweb', 'ericlimer', 'robschoon', 'davidnield', 'conger', 'kcampbelldollaghan', 'rmisra', 'kyle-vanhemert-old', 'rtgonzalez', 'rhettjonesgizmodo', 'hudsonhongo', 'williamturton', 'john-herrman-old', 'leahbecerra', 'michaelfnunez', 'alexcranz', 'bryanlufkin', 'ace', 'estheringlis-arkell', 'acovert31', 'evepeyser', 'robertsorokanich', 'georgedvorsky', 'carlivelocci', 'jcondliffe', 'sophiekleeman', 'sean-fallon-old', 'knibbs', 'tommckay', 'dellcam', 'libbywatson', 'Mark-Strauss', 'nicolewetsman', 'melaniehannah', 'annaleenewitz', 'ashleyfeinberg'] | |
# for writer in writers: | |
# webbrowser.open("https://kinja.com/{}".format(writer)) | |
""" | |
<div class="large-4 columns sidebar"><div class="sidebar-container js_sidebar-actual-container"><div class="secondary-nav-btn-wrapper hide-for-large-up js_secondary-nav-btn-wrapper transition"><a class="secondary-nav__item secondary-nav__item--inline js_toggle-secondary-nav icon--svg u-darkened">Posts<svg class="svg-icon svg-chevron chevron--bottom"><use xlink:href="#iconset-chevron-bottom"></use></svg></a></div><div itemscope="" itemtype="http://schema.org/Person" class="sidebar-header row"><div class="column"><div class="row"><div class="column"><div class="profile-avatar" style="background-image: url(https://i.kinja-img.com/gawker-media/image/upload/s--v_un4kjb--/c_fill,fl_progressive,g_center,h_200,q_80,w_200/byofaowfchgc8oisypcx.jpg)"></div><img itemprop="image" src="https://i.kinja-img.com/gawker-media/image/upload/s--v_un4kjb--/c_fill,fl_progressive,g_center,h_200,q_80,w_200/byofaowfchgc8oisypcx.jpg" style="display:none;"></div></div><div class="row"><div class="column"><div itemprop="name" class="profile-displayname text-center">Bryan Menegus</div><div itemprop="alternateName" class="profile-screenname text-center"><svg class="svg-icon svg-user"><use xlink:href="#iconset-user"></use></svg>fruitsoftheweb</div><div class="follow-controls follow-controls--profile js_user-follow-controls" data-authorid="5876237249236384217"><a href="#" data-analytics-target="profileLeftBar" data-action="follow" class="js_followforuser button small list-entity__button--follow icon--svg list-control " data-ga="[Profile Page, Follow Link Click, js_pageType]"><span>Follow</span><svg class="svg-icon small svg-add--small"><use xlink:href="#iconset-add--small"></use></svg></a><a href="#" data-analytics-target="profileLeftBar" data-action="unfollow" class="js_unfollowforuser button small list-entity__button--following icon--svg list-control following list-control--active hide"><span>Following</span><svg class="svg-icon small svg-checkmark--small"><use xlink:href="#iconset-checkmark--small"></use></svg></a></div></div></div><div class="row"><div class="column"><div class="user-details"><p class="user-details__bio">Senior reporter | |
</p><div class="user-details__links"><a class="user-details__twitter user-details--flair" href="https://twitter.com/BryanDisagrees" title="Twitter Handle" target="_blank"><svg class="svg-icon svg-icon--filled svg-twitter"><use xlink:href="#iconset-twitter"></use></svg>@BryanDisagrees</a></div><hr><div class="user-details__crypto"><p>PGP Fingerprint: 1905 9104 D967 2EB7 C3F5 68F9 9108 1434 C917 C1B9</p></div></div></div></div><div class="row"><div class="column sidebar-follow small-6 text-center"><a href="/fruitsoftheweb/followers" class="sidebar-follow__link">Followers (447)</a></div><div class="column sidebar-follow small-6 text-center"><a href="/fruitsoftheweb/following" class="sidebar-follow__link">Following (3)</a></div></div></div></div><div class="row hide-for-medium-down"><div class="column"><ul class="sidebar-nav__list"><li class="sidebar-nav__item active"><a class="sidebar-nav__link" href="/fruitsoftheweb/posts">Posts<svg class="svg-icon svg-chevron chevron--right"><use xlink:href="#iconset-chevron-right"></use></svg></a></li><li class="sidebar-nav__item"><a class="sidebar-nav__link" href="/fruitsoftheweb/discussions">Discussions<svg class="svg-icon svg-chevron chevron--right"><use xlink:href="#iconset-chevron-right"></use></svg></a></li><li class="sidebar-nav__item"><a class="sidebar-nav__link" href="/fruitsoftheweb/saved">Saved Articles<svg class="svg-icon icon-bookmark"><use xlink:href="#iconset-bookmark"></use></svg><svg class="svg-icon svg-chevron chevron--right"><use xlink:href="#iconset-chevron-right"></use></svg></a></li></ul></div></div></div></div>4 | |
""" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment