请帮助我解决这个小问题。我正在寻找使用美丽的汤(Python)或python从SCRIPT标记(而不是Body)中的下面的代码中提取lat和lng值。我是Python新手,博客推荐使用美丽的汤来提取。如何使用Python或beautifulsoup从文件中提取文本(使用脚本标记)
我想这两个值纬度:21.25335,经度:81.649445 我使用正则表达式这一点。我的正规表示“^ L([在])(:)([0-9])([^,] +)”
检查此链接为正则表达式和HTML文件 - http://regexr.com/3glde
我用这个正则表达式得到了这两个值,但我只想把那些lat和lng值(数字部分)存储在变量中。
这里下面是我用我的Python代码
import re
pattern = re.compile("^[l]([a-t])([a-t])(\:) ([0-9])([^,]+)")
for i, line in enumerate(open('C:\hile_text.html')):
for match in re.finditer(pattern, line):
print 'Found on line %s: %s' % (i+1, match.groups())
输出:
- 实测值线3218:( 'A', 'T', ':', '2' '1.244791')
- 实测值线3219:( 'N', 'G', ':', '8', '1.643486')
我想只有那些数值像21.25335输出,81 .649445并且想要将这些值存储在变量中,否则您可以为此提供替代代码。
plzz很快帮助我。感谢预期。
这是HTML文件中的脚本标记。
<script type="text/javascript">
window.mapDivId = 'map0Div';
window.map0Div = {
lat: 21.25335,
lng: 81.649445,
zoom: null,
locId: 5897747,
geoId: 297595,
isAttraction: false,
isEatery: true,
isLodging: false,
isNeighborhood: false,
title: "Aman Age Roll & Chicken ",
homeIcon: true,
url: "/Restaurant_Review-g297595-d5897747-Reviews-Aman_Age_Roll_Chicken-Raipur_Raipur_District_Chhattisgarh.html",
minPins: [
['hotel', 20],
['restaurant', 20],
['attraction', 20],
['vacation_rental', 0] ],
units: 'km',
geoMap: false,
tabletFullSite: false,
reuseHoverDivs: false,
noSponsors: true };
ta.store('infobox_js', 'https://static.tacdn.com/js3/infobox-c-v21051733989b.js');
ta.store("ta.maps.apiKey", "");
(function() {
var onload = function() {
if (window.location.hash == "#MAPVIEW") {
ta.run("ta.mapsv2.Factory.handleHashLocation", {}, true);
}
}
if (window.addEventListener) {
if (window.history && window.history.pushState) {
window.addEventListener("popstate", function(e) {
ta.run("ta.mapsv2.Factory.handleHashLocation", {}, false);
}, false);
}
window.addEventListener('load', onload, false);
}
else if (window.attachEvent) {
window.attachEvent('onload', onload);
}
})();
ta.store("mapsv2.show_sidebar", true);
ta.store('mapsv2_restaurant_reservation_js', ["https://static.tacdn.com/js3/ta-mapsv2-restaurant-reservation-c-v2430632369b.js"]);
ta.store('mapsv2.typeahead_css', "https://static.tacdn.com/css2/maps_typeahead-v21940478230b.css");
// Feature gate VR price pins on SRP map. VRC-14803
ta.store('mapsv2.vr_srp_map_price_enabled', true);
ta.store('mapsv2.geoName', 'Raipur');
ta.store('mapsv2.map_addressnotfound', "Address not found"); ta.store('mapsv2.map_addressnotfound3', "We couldn\'t find that location near {0}. Please try another search."); ta.store('mapsv2.directions', "Directions from {0} to {1}"); ta.store('mapsv2.enter_dates', "Enter dates for best prices"); ta.store('mapsv2.best_prices', "Best prices for your stay"); ta.store('mapsv2.list_accom', "List of accommodations"); ta.store('mapsv2.list_hotels', "List of hotels"); ta.store('mapsv2.list_vrs', "List of holiday rentals"); ta.store('mapsv2.more_accom', "More accommodations"); ta.store('mapsv2.more_hotels', "More hotels"); ta.store('mapsv2.more_vrs', "More Holiday Homes"); ta.store('mapsv2.sold_out_on_1', "SOLD OUT on 1 site"); ta.store('mapsv2.sold_out_on_y', "SOLD OUT on 2 sites"); </script>
“(L [一个] [GT])(:\ S +)(\ d + \ \ d +)” 这种表达现在工作 –
大。你能否将我的答案标记为已接受? – WombatPM